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

    Neuronpedia

    INDEX
    Explanations

    changes or variations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pawn
    -0.07
     designing
    -0.07
    CEO
    -0.07
     Aur
    -0.06
     Laser
    -0.06
     Tob
    -0.06
     porn
    -0.06
    _ob
    -0.06
    ینی
    -0.06
     functionalities
    -0.06
    POSITIVE LOGITS
    خف
    0.07
     العظ
    0.07
     poč
    0.06
    .labelControl
    0.06
    getRoot
    0.06
    _al
    0.06
    えて
    0.06
    -an
    0.06
     Một
    0.06
    :SetText
    0.06
    Act Density 0.036%

    No Known Activations