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

    Neuronpedia

    INDEX
    Explanations

    button

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Sql
    -0.06
    急
    -0.06
    ленный
    -0.06
     αρ
    -0.06
    Concern
    -0.06
     тепер
    -0.06
     Kov
    -0.06
    _middle
    -0.06
     따라
    -0.06
     sordu
    -0.06
    POSITIVE LOGITS
    (bytes
    0.07
    mate
    0.07
    /TR
    0.06
    ARSE
    0.06
    <Tuple
    0.06
     aktuální
    0.06
    -create
    0.06
     Foto
    0.06
     Harden
    0.06
    ρωπα
    0.06
    Act Density 0.000%

    No Known Activations