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

    Neuronpedia

    INDEX
    Explanations

    USE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .want
    -0.07
     yat
    -0.06
     unsur
    -0.06
    相同
    -0.06
    _person
    -0.06
    介
    -0.06
     дій
    -0.06
    zeň
    -0.06
    ateria
    -0.06
     expl
    -0.06
    POSITIVE LOGITS
     investments
    0.07
     depths
    0.07
    <Field
    0.06
     INTERRUPTION
    0.06
    vim
    0.06
     MIN
    0.06
    UINT
    0.06
    registered
    0.06
    spam
    0.06
    ALAR
    0.06
    Act Density 0.002%

    No Known Activations