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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Julien
    -0.08
     adding
    -0.07
    喃
    -0.07
    Scale
    -0.07
     follic
    -0.07
     bộ
    -0.07
    尼斯
    -0.07
    .setAlignment
    -0.07
     Jesús
    -0.07
    oulouse
    -0.07
    POSITIVE LOGITS
    !--
    0.07
     매
    0.06
    �
    0.06
    爇
    0.06
    )$/
    0.06
    adapter
    0.06
    דג
    0.06
    習慣
    0.06
    🎶
    0.06
     wg
    0.06
    Act Density 0.003%

    No Known Activations