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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    万里
    -0.08
    umblr
    -0.07
     helpless
    -0.07
    �
    -0.07
    �다
    -0.07
    мя
    -0.07
     baseUrl
    -0.07
    빴
    -0.06
    _NAME
    -0.06
    韂
    -0.06
    POSITIVE LOGITS
    fab
    0.07
     UW
    0.06
    讓
    0.06
    .Qual
    0.06
    Reflection
    0.06
     Criterion
    0.06
     Raised
    0.06
     Bin
    0.06
     Station
    0.06
     trunc
    0.06
    Act Density 0.003%

    No Known Activations