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

    Neuronpedia

    INDEX
    Explanations

    Stanley

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OURSE
    -0.08
    adget
    -0.08
    둘
    -0.08
    𬃊
    -0.08
    addTo
    -0.07
    少吃
    -0.07
    ">@
    -0.07
    _self
    -0.07
    mitter
    -0.07
    CSR
    -0.06
    POSITIVE LOGITS
    花钱
    0.07
    DIC
    0.07
    פתח
    0.07
     לפתוח
    0.07
    .Re
    0.06
     /\.
    0.06
    (fill
    0.06
    열
    0.06
     repar
    0.06
     fiss
    0.06
    Act Density 0.001%

    No Known Activations