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

    Neuronpedia

    INDEX
    Explanations

    expectations and limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -defense
    -0.07
     án
    -0.07
    ="%
    -0.07
    /gtest
    -0.06
    searchModel
    -0.06
    <<<
    -0.06
    .conditions
    -0.06
    ackle
    -0.06
     نفسه
    -0.06
    _nc
    -0.06
    POSITIVE LOGITS
     Cuba
    0.07
    .ForeColor
    0.07
    >);↵
    0.06
     RTL
    0.06
    abol
    0.06
     Karachi
    0.06
    _DEV
    0.06
    จ
    0.06
     Ebony
    0.06
     fade
    0.06
    Act Density 0.046%

    No Known Activations