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

    Neuronpedia

    INDEX
    Explanations

    ind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =item
    -0.08
    �
    -0.08
     tener
    -0.07
    Mensaje
    -0.07
    tight
    -0.07
    iltro
    -0.07
    روف
    -0.07
     احد
    -0.07
     requestOptions
    -0.07
    _todo
    -0.07
    POSITIVE LOGITS
    .opend
    0.08
     Dorm
    0.08
    ))[
    0.08
    展开
    0.07
     inadvert
    0.07
    低迷
    0.07
    TP
    0.06
    -cont
    0.06
     Guardians
    0.06
    ])
↵
    0.06
    Act Density 0.006%

    No Known Activations