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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ighton
    -0.06
     exponential
    -0.06
    ')))
    -0.06
    —not
    -0.06
    ratings
    -0.06
    映
    -0.06
     مسئول
    -0.06
    _relations
    -0.06
    枚
    -0.06
     cone
    -0.06
    POSITIVE LOGITS
     Bien
    0.07
     suis
    0.07
     throm
    0.06
    ellation
    0.06
    usion
    0.06
    -access
    0.06
    StateToProps
    0.06
     iş
    0.06
    ....
    0.06
    titre
    0.06
    Act Density 0.055%

    No Known Activations