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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _directory
    -0.07
    �t
    -0.07
     Termin
    -0.06
    Record
    -0.06
    �
    -0.06
    _version
    -0.06
    wor
    -0.06
     Encyclopedia
    -0.06
    定的
    -0.06
    (Y
    -0.06
    POSITIVE LOGITS
    exampleInputEmail
    0.07
     Clin
    0.07
    _mutex
    0.06
     quem
    0.06
    -tip
    0.06
     neo
    0.06
    -stage
    0.06
    Ư
    0.06
    濃
    0.06
     nem
    0.06
    Act Density 0.068%

    No Known Activations