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

    Neuronpedia

    INDEX
    Explanations

    drops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    金属
    -0.07
     Pavilion
    -0.07
    .level
    -0.07
     helmet
    -0.06
    より
    -0.06
     měli
    -0.06
    (recv
    -0.06
    ær
    -0.06
    كرة
    -0.06
    ivid
    -0.06
    POSITIVE LOGITS
    �
    0.07
     disappointed
    0.07
     Αθή
    0.07
    傷
    0.06
    .exception
    0.06
     सरक
    0.06
    ){}↵
    0.06
     drops
    0.06
     observations
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations