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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    objectId
    -0.07
     Washing
    -0.06
     Unsure
    -0.06
     Application
    -0.06
    éro
    -0.06
     anonymity
    -0.06
    ЕР
    -0.06
    _EFFECT
    -0.06
    ,title
    -0.06
     inhibition
    -0.06
    POSITIVE LOGITS
     почти
    0.06
     พฤษภาคม
    0.06
     đàn
    0.06
    ватися
    0.06
    名稱
    0.06
    CallCheck
    0.06
     wij
    0.06
    /random
    0.06
    ually
    0.06
    Ham
    0.06
    Act Density 0.085%

    No Known Activations