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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ertiary
    -0.07
    URRED
    -0.07
     البر
    -0.07
    .BAD
    -0.06
    _SURFACE
    -0.06
     Rank
    -0.06
     Himself
    -0.06
     tertiary
    -0.06
     nitelik
    -0.06
    ấp
    -0.06
    POSITIVE LOGITS
    _timer
    0.07
    HD
    0.07
    bastian
    0.07
    民
    0.06
    [^
    0.06
    egt
    0.06
    えない
    0.06
    ,\"
    0.06
    ::::/
    0.06
    ghi
    0.06
    Act Density 0.001%

    No Known Activations