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

    Neuronpedia

    INDEX
    Explanations

    Informal writing/conversational

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DataSet
    -0.07
     PUR
    -0.07
    ordum
    -0.06
    Predict
    -0.06
    .Iter
    -0.06
     hasattr
    -0.06
    ,retain
    -0.06
    /change
    -0.06
     stocked
    -0.06
    (In
    -0.06
    POSITIVE LOGITS
     برج
    0.07
    [((
    0.06
    712
    0.06
    Trace
    0.06
    .toLocale
    0.06
     happens
    0.05
     enjoyable
    0.05
    Bre
    0.05
     endorsed
    0.05
     उ
    0.05
    Act Density 0.120%

    No Known Activations