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

    Neuronpedia

    INDEX
    Explanations

    Math constants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    普查
    -0.07
     machining
    -0.07
     filmpjes
    -0.07
    culture
    -0.07
     brush
    -0.07
     setStatus
    -0.07
    films
    -0.06
    imagen
    -0.06
    טייל
    -0.06
    远景
    -0.06
    POSITIVE LOGITS
    )"↵↵
    0.08
    七
    0.07
     Mot
    0.07
    >';↵
    0.07
    *,
    0.07
    "↵↵↵
    0.07
    )"
    0.07
    -git
    0.07
    )();↵
    0.06
    ...↵↵↵
    0.06
    Act Density 0.006%

    No Known Activations