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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    标题
    -0.07
    fort
    -0.07
     reloading
    -0.06
     barbar
    -0.06
     Mental
    -0.06
     meille
    -0.06
    artner
    -0.06
     fifteen
    -0.06
    likleri
    -0.06
    健
    -0.06
    POSITIVE LOGITS
    _navigation
    0.07
     هد
    0.06
    ombie
    0.06
    categorias
    0.06
    ^{
    0.06
     Variable
    0.06
     vaccinated
    0.06
     đối
    0.06
    _this
    0.06
    τύ
    0.06
    Act Density 0.003%

    No Known Activations