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

    Neuronpedia

    INDEX
    Explanations

    Ages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acco
    -0.07
    (lo
    -0.06
    division
    -0.06
    -0.06
    INCLUDING
    -0.06
     vàng
    -0.06
    .wx
    -0.06
    MainThread
    -0.06
    .segments
    -0.06
    Called
    -0.06
    POSITIVE LOGITS
    ासन
    0.07
     SEXP
    0.07
     °
    0.06
    .toggle
    0.06
     Kathy
    0.06
     atrav
    0.06
    чины
    0.06
    :".$
    0.06
     пам
    0.06
     cherche
    0.06
    Act Density 0.024%

    No Known Activations