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

    Neuronpedia

    INDEX
    Explanations

    book reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redesigned
    -0.07
    ᒃ
    -0.07
     Either
    -0.07
    合资
    -0.06
    Called
    -0.06
     dang
    -0.06
    ʨ
    -0.06
     DIAG
    -0.06
    deb
    -0.06
    ulp
    -0.06
    POSITIVE LOGITS
     subjective
    0.08
    _CONVERT
    0.08
     Bob
    0.07
    的精神
    0.07
     crews
    0.07
     wrists
    0.07
    CHANNEL
    0.07
     Chat
    0.07
    肋
    0.06
     Batt
    0.06
    Act Density 0.104%

    No Known Activations