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

    Neuronpedia

    INDEX
    Explanations

    lik

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     database
    -0.07
    قدرة
    -0.07
     unleashed
    -0.07
    placed
    -0.07
     sécurité
    -0.06
    ández
    -0.06
     atop
    -0.06
    只有
    -0.06
    adera
    -0.06
    اخل
    -0.06
    POSITIVE LOGITS
    /&
    0.07
     vals
    0.07
    itized
    0.07
    _TV
    0.07
    /fixtures
    0.07
     `{
    0.07
    联谊
    0.07
    /forms
    0.06
    �
    0.06
     nrw
    0.06
    Act Density 0.001%

    No Known Activations