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

    Neuronpedia

    INDEX
    Explanations

    Type suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     maths
    -0.07
     Caucasian
    -0.06
     erotisk
    -0.06
     فراو
    -0.06
    ΡΙ
    -0.06
     بنا
    -0.06
    ools
    -0.06
    _chain
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _APB
    0.07
     infection
    0.07
    .Sprintf
    0.06
    Experiment
    0.06
    GY
    0.06
    Winvalid
    0.06
     ;
↵
    0.06
    (async
    0.06
    /sidebar
    0.06
    """
↵
    0.06
    Act Density 0.001%

    No Known Activations