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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肖
    -0.06
     ل
    -0.06
     Frances
    -0.06
     GetType
    -0.06
    LY
    -0.06
    ٤
    -0.06
     DEST
    -0.06
    关于
    -0.06
    ोर
    -0.06
    CI
    -0.06
    POSITIVE LOGITS
    Gratis
    0.07
     Podesta
    0.07
     blamed
    0.06
     Papa
    0.06
     Parser
    0.06
     默认
    0.06
    oons
    0.06
    ange
    0.06
    (predicate
    0.06
     escorted
    0.06
    Act Density 0.001%

    No Known Activations