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

    Neuronpedia

    INDEX
    Explanations

    Code/mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    én
    -0.07
    browse
    -0.07
     zb
    -0.07
    travel
    -0.07
    OPLE
    -0.06
    TextStyle
    -0.06
    ERE
    -0.06
    💘
    -0.06
    $/)
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
    嚴
    0.08
    رى
    0.07
     posterior
    0.07
    框架
    0.07
    .iloc
    0.07
    부
    0.07
     glowing
    0.06
    🤹
    0.06
    /effects
    0.06
    楗
    0.06
    Act Density 0.002%

    No Known Activations