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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     underscores
    -0.08
    War
    -0.07
     Aber
    -0.07
     NGX
    -0.06
     bout
    -0.06
    Psych
    -0.06
     deflect
    -0.06
    wald
    -0.06
    Conference
    -0.06
    _mc
    -0.06
    POSITIVE LOGITS
    /libs
    0.07
     ischem
    0.07
     وغير
    0.06
    .about
    0.06
    oggle
    0.06
     --↵↵
    0.06
     Ев
    0.06
     تعریف
    0.06
     glGetUniformLocation
    0.06
     đẩy
    0.06
    Act Density 0.001%

    No Known Activations