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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or acknowledgment

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

    Follows "to," "just," or "me."

    np_acts-logits-general · gemini-2.0-flash

    just want to point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الإنجليزية
    -0.81
    Datuak
    -0.79
    OGND
    -0.76
    Geplaatst
    -0.75
     <",
    -0.72
     незавершена
    -0.72
    Abitanti
    -0.70
     resourceCulture
    -0.70
    ⟬
    -0.68
    Попис
    -0.68
    POSITIVE LOGITS
     remind
    0.56
     highlight
    0.55
    ponses
    0.54
     reiterate
    0.52
     briefly
    0.51
    Aiheesta
    0.50
     challenge
    0.49
     brief
    0.48
     duy
    0.48
     few
    0.47
    Act Density 0.139%

    No Known Activations