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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motor
    -0.07
     intercourse
    -0.07
    posting
    -0.06
     feet
    -0.06
    Ế
    -0.06
    FER
    -0.06
    Vtbl
    -0.06
    IMP
    -0.06
    变化
    -0.06
     mountains
    -0.06
    POSITIVE LOGITS
    _weak
    0.07
    _this
    0.07
    .span
    0.07
     womens
    0.06
     langu
    0.06
    [hash
    0.06
    桌
    0.06
     розгля
    0.06
    389
    0.06
    ruž
    0.06
    Act Density 0.034%

    No Known Activations