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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eller
    -0.07
     diplomatic
    -0.07
    andid
    -0.06
    olon
    -0.06
    ством
    -0.06
    자의
    -0.06
    .Temp
    -0.06
     guten
    -0.06
    стві
    -0.06
    џ
    -0.06
    POSITIVE LOGITS
     Rutgers
    0.06
    Qty
    0.06
     reducers
    0.06
    PushMatrix
    0.06
    Trivia
    0.06
     Dies
    0.06
     chlor
    0.06
    reveal
    0.06
     HTTPS
    0.06
     believed
    0.06
    Act Density 0.076%

    No Known Activations