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

    Neuronpedia

    INDEX
    Explanations

    ████

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _books
    -0.07
    ensaje
    -0.07
    nob
    -0.07
    ettes
    -0.07
    _nsec
    -0.07
    etrain
    -0.07
    NET
    -0.06
    trait
    -0.06
    unable
    -0.06
    ------
    -0.06
    POSITIVE LOGITS
     Willi
    0.07
    peror
    0.06
     dedi
    0.06
    zcze
    0.06
     tüket
    0.06
     stanza
    0.06
     perpetrated
    0.06
    kan
    0.06
    ":↵
    0.05
    .deltaTime
    0.05
    Act Density 0.000%

    No Known Activations