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

    Neuronpedia

    INDEX
    Explanations

    Gruff exterior/resistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Enemy
    -0.07
     Lecture
    -0.07
    رن
    -0.07
     signup
    -0.07
    ск
    -0.07
     curator
    -0.07
    -im
    -0.07
     dậy
    -0.06
    锎
    -0.06
     authored
    -0.06
    POSITIVE LOGITS
    حاسب
    0.07
    .annotations
    0.07
    .filters
    0.07
    Roll
    0.07
    成長
    0.07
     TELE
    0.07
    荷
    0.07
    conditional
    0.07
    诱导
    0.06
    纪检
    0.06
    Act Density 0.130%

    No Known Activations