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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pulver
    -0.07
     colour
    -0.06
     Caption
    -0.06
    .esp
    -0.06
     binary
    -0.06
    /her
    -0.06
     vary
    -0.06
    ()){
    -0.06
     gastr
    -0.05
     Beg
    -0.05
    POSITIVE LOGITS
    レン
    0.08
    license
    0.07
    WN
    0.07
    roll
    0.07
    ansa
    0.06
    lit
    0.06
    crime
    0.06
    лей
    0.06
    ladığı
    0.06
     rifles
    0.06
    Act Density 0.000%

    No Known Activations