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

    Neuronpedia

    INDEX
    Explanations

    statistical probability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ll
    -0.07
    含有
    -0.07
    多地
    -0.06
    سام
    -0.06
    acman
    -0.06
     technically
    -0.06
    您可以
    -0.06
     harmless
    -0.06
    conference
    -0.06
     graduated
    -0.06
    POSITIVE LOGITS
    ✮
    0.08
    [player
    0.08
    倪
    0.07
    鹪
    0.07
    汐
    0.07
    𝙶
    0.07
     twentieth
    0.07
    .loop
    0.07
    덞
    0.07
    書き
    0.07
    Act Density 0.049%

    No Known Activations