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

    Neuronpedia

    INDEX
    Explanations

    64

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Temp
    -0.07
    mploy
    -0.06
    ेशन
    -0.06
     трансп
    -0.06
     nonetheless
    -0.06
     Zion
    -0.06
    GROUP
    -0.06
    locking
    -0.06
    stored
    -0.06
     成
    -0.06
    POSITIVE LOGITS
     vulgar
    0.13
     дум
    0.10
    /svg
    0.09
     Hmm
    0.08
    leDb
    0.08
    Hmm
    0.08
    64
    0.07
     уже
    0.07
     рус
    0.07
     rotary
    0.07
    Act Density 0.004%

    No Known Activations