Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    concepts related to gratitude and appreciation for collaboration and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "have," "an," or "of"

    np_acts-logits-general · gemini-2.0-flash

    celebrities and positive descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ัพท์
    -0.55
    COUVER
    -0.54
     eventuell
    -0.54
     resourceCulture
    -0.53
    الإنجليزية
    -0.53
     barnet
    -0.53
    LookAndFeel
    -0.53
     strings
    -0.52
    '">
    -0.51
     preference
    -0.50
    POSITIVE LOGITS
     wonderful
    1.21
    wonderful
    1.17
     amazing
    1.12
    amazing
    1.04
     fantastic
    0.99
     wspania
    0.95
     incredible
    0.94
    Wonderful
    0.94
    incredible
    0.93
     beautiful
    0.91
    Act Density 0.180%

    No Known Activations