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
    如下
    -0.07
     стандарт
    -0.06
    扱
    -0.06
    чай
    -0.06
    _PROPERTIES
    -0.06
     related
    -0.06
     Ide
    -0.06
     homeowners
    -0.06
     bohat
    -0.06
     بين
    -0.06
    POSITIVE LOGITS
    getView
    0.07
    inha
    0.07
    .sulake
    0.07
     Lesb
    0.07
    σσ
    0.07
    ulario
    0.06
    eva
    0.06
     آبی
    0.06
    eee
    0.06
    ī
    0.06
    Act Density 0.058%

    No Known Activations