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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fundamental
    -0.07
    _VALUE
    -0.07
     OR
    -0.07
     Playground
    -0.07
    ЎыџN
    -0.07
     Romero
    -0.07
     Consortium
    -0.07
     butt
    -0.06
    模型
    -0.06
    μμ
    -0.06
    POSITIVE LOGITS
     vậy
    0.08
    ریز
    0.07
     -->↵↵
    0.06
     -->↵
    0.06
    stry
    0.06
    —is
    0.06
    istration
    0.06
     교
    0.06
    _Server
    0.06
    .NotNull
    0.06
    Act Density 0.017%

    No Known Activations