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

    Neuronpedia

    INDEX
    Explanations

    Decimal digits and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iche
    -0.08
    inoa
    -0.08
    elin
    -0.07
     Gam
    -0.07
    chen
    -0.07
     clas
    -0.07
    ivent
    -0.07
     Giant
    -0.07
     bour
    -0.07
    -0.07
    POSITIVE LOGITS
    Aantal
    0.09
     longueur
    0.09
    0.08
     trailing
    0.08
    Trailing
    0.08
    Zeros
    0.08
    Depth
    0.08
     długo
    0.08
     panjang
    0.08
    Specified
    0.08
    Act Density 0.016%
    No Known Activations