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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orgetown
    -0.07
    顽强
    -0.07
    𫚭
    -0.07
    终点
    -0.07
    cliffe
    -0.07
    נייד
    -0.07
     McDonald
    -0.07
    stellen
    -0.07
     Barang
    -0.07
     immobil
    -0.06
    POSITIVE LOGITS
    avorites
    0.07
     isNaN
    0.07
    涨幅
    0.06
    /table
    0.06
     Quickly
    0.06
     pequeña
    0.06
    (floor
    0.06
    ssue
    0.06
     Tournament
    0.06
     ella
    0.06
    Act Density 0.063%

    No Known Activations