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

    Neuronpedia

    INDEX
    Explanations

    Article snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     address
    -0.07
    ({});↵
    -0.07
    agher
    -0.07
    _ranges
    -0.07
    (skb
    -0.07
     Cannon
    -0.06
    attrs
    -0.06
     ."
    -0.06
     express
    -0.06
     wrapper
    -0.06
    POSITIVE LOGITS
    休闲
    0.07
    學生
    0.07
    Глав
    0.07
    ˡ
    0.07
    生
    0.07
    >The
    0.07
     그리스도
    0.07
     entrar
    0.07
    高校
    0.07
    @Slf
    0.07
    Act Density 0.030%

    No Known Activations