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

    Neuronpedia

    INDEX
    Explanations

    when something does not make logical "sense"

    oai_token-act-pair · gemini-2.0-flash

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    matchCondition
    -0.59
     发表于
    -0.56
     SENSE
    -0.55
     Sense
    -0.55
     sense
    -0.54
     appropriateness
    -0.53
    Xna
    -0.51
    rouvez
    -0.50
    leman
    -0.50
    ropriate
    -0.50
    POSITIVE LOGITS
     purpoſe
    0.66
    Personendaten
    0.65
     ſtate
    0.63
     Shakspeare
    0.61
    TargetException
    0.60
     ſtre
    0.60
     effusion
    0.60
    AndEndTag
    0.59
     incest
    0.59
     ſhe
    0.59
    Act Density 10.456%

    No Known Activations