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

    Neuronpedia

    INDEX
    Explanations

    buttocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orang
    -0.07
    直接
    -0.06
     abortion
    -0.06
    Normalize
    -0.06
    contenido
    -0.06
    ?>↵↵
    -0.06
     characterize
    -0.06
    _LS
    -0.06
    (Group
    -0.06
    (arr
    -0.06
    POSITIVE LOGITS
    apphire
    0.09
    muz
    0.07
    illion
    0.07
    ELY
    0.06
     shootings
    0.06
    ,false
    0.06
    стве
    0.06
    /sec
    0.06
    ภาพยนตร
    0.06
    Events
    0.06
    Act Density 0.009%

    No Known Activations