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

    Neuronpedia

    INDEX
    Explanations

    itive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cadena
    -0.08
    (vals
    -0.07
     ува
    -0.07
    孤
    -0.07
     until
    -0.06
     xung
    -0.06
    LEAN
    -0.06
     PIXI
    -0.06
     Huang
    -0.06
     orphan
    -0.06
    POSITIVE LOGITS
    committee
    0.07
    .PropertyType
    0.07
    striction
    0.06
    urve
    0.06
    ivre
    0.06
    rokes
    0.06
    百
    0.06
    тивного
    0.06
     Licensing
    0.06
    pliant
    0.06
    Act Density 0.001%

    No Known Activations