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

    Neuronpedia

    INDEX
    Explanations

    source code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .idx
    -0.07
    specs
    -0.07
     Ps
    -0.07
    ToFile
    -0.07
    点了点头
    -0.06
    تردد
    -0.06
     międzynar
    -0.06
    -op
    -0.06
    沐浴
    -0.06
    Hip
    -0.06
    POSITIVE LOGITS
     ritual
    0.08
    _RULE
    0.08
    藏
    0.07
    WARE
    0.07
    aren
    0.07
     hashing
    0.07
    uela
    0.07
    _role
    0.07
     monopol
    0.07
     quotas
    0.07
    Act Density 0.001%

    No Known Activations