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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ⴆ
    -0.07
    홋
    -0.07
    resse
    -0.07
    .av
    -0.07
    -desc
    -0.07
    .getSession
    -0.07
    新手
    -0.07
    -counter
    -0.07
    liked
    -0.07
     Phrase
    -0.07
    POSITIVE LOGITS
    員
    0.07
    قدير
    0.07
     định
    0.07
     erotici
    0.07
    预测
    0.06
     General
    0.06
    ibernate
    0.06
    uries
    0.06
    thesize
    0.06
    大巴
    0.06
    Act Density 0.000%

    No Known Activations