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

    Neuronpedia

    INDEX
    Explanations

    code/configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snapshot
    -0.08
    茚
    -0.08
     Isl
    -0.07
    antt
    -0.07
     diagnose
    -0.07
     probable
    -0.07
     ashamed
    -0.07
     pastoral
    -0.07
    羔
    -0.07
    高血压
    -0.07
    POSITIVE LOGITS
    _raise
    0.07
    もあり
    0.06
    的基础上
    0.06
    山东
    0.06
    .CreateCommand
    0.06
    าง
    0.06
     rog
    0.06
    结尾
    0.06
    孖
    0.06
    sterreich
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.