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

    Neuronpedia

    INDEX
    Explanations

    personal messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erm
    -0.08
    赈
    -0.07
    Ǿ
    -0.07
     Presidency
    -0.07
    rising
    -0.07
    将领
    -0.07
     несколько
    -0.07
     defeats
    -0.06
     дополн
    -0.06
    做得
    -0.06
    POSITIVE LOGITS
    冢
    0.07
     Lik
    0.07
    ecimal
    0.07
    bin
    0.07
     [:
    0.06
    Cycle
    0.06
    ви
    0.06
    み
    0.06
    0.06
     runoff
    0.06
    Act Density 0.101%

    No Known Activations