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

    Neuronpedia

    INDEX
    Explanations

    alias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sabb
    -0.07
     inté
    -0.07
    Winter
    -0.07
    깸
    -0.07
    )|(
    -0.06
     davon
    -0.06
    햬
    -0.06
    ஓ
    -0.06
     stellen
    -0.06
     자
    -0.06
    POSITIVE LOGITS
    _argv
    0.07
    古怪
    0.07
    륨
    0.07
    ptoms
    0.07
     Peel
    0.07
    OCKET
    0.07
    okit
    0.07
    较好
    0.06
    _ACTIVITY
    0.06
    Tipo
    0.06
    Act Density 0.324%

    No Known Activations