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

    Neuronpedia

    INDEX
    Explanations

    Java serialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ahead
    -0.07
     frightening
    -0.07
    mk
    -0.07
     TN
    -0.07
     tan
    -0.07
     Nad
    -0.06
     demanding
    -0.06
    都不敢
    -0.06
    aed
    -0.06
    げ
    -0.06
    POSITIVE LOGITS
    日期
    0.07
     viết
    0.07
    whereIn
    0.07
    妯
    0.07
     pulver
    0.07
    㐂
    0.07
     données
    0.06
    诽
    0.06
    萁
    0.06
    شاب
    0.06
    Act Density 0.005%

    No Known Activations