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

    Neuronpedia

    INDEX
    Explanations

    Data clustering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cyril
    -0.07
    者の
    -0.07
    人次
    -0.07
     classname
    -0.07
    ipped
    -0.07
    兵力
    -0.07
    心灵
    -0.07
    braska
    -0.07
    Female
    -0.07
    Anne
    -0.07
    POSITIVE LOGITS
    אונ
    0.07
    ("""
    0.07
    (mc
    0.07
    (found
    0.07
    _stdout
    0.07
    骧
    0.07
    ﰃ
    0.06
    (eq
    0.06
    _process
    0.06
    _Float
    0.06
    Act Density 0.006%

    No Known Activations