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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions and personal reflections

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

    Positive sentiment/opinion

    np_acts-logits-general · gemini-2.0-flash

    positive and negative evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zarchiwizowane
    -0.76
    mybatisplus
    -0.70
    nationality
    -0.56
     hivyo
    -0.56
    ztály
    -0.55
    UMBIA
    -0.55
    SizeF
    -0.54
    ご注意
    -0.53
     gerne
    -0.51
     متعلقه
    -0.51
    POSITIVE LOGITS
     seeing
    1.35
     having
    1.33
     knowing
    1.30
     hearing
    1.26
     Having
    1.18
    having
    1.17
    Having
    1.14
     being
    1.12
     watching
    1.09
    seeing
    1.08
    Act Density 0.234%

    No Known Activations