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
     Бер
    -0.07
    tensor
    -0.06
    authorization
    -0.06
     outfile
    -0.06
     getPrice
    -0.06
    もり
    -0.06
     Vad
    -0.06
    _request
    -0.06
    components
    -0.06
    _partition
    -0.06
    POSITIVE LOGITS
    arat
    0.07
     stealth
    0.06
    _mB
    0.06
     fourn
    0.06
     Thổ
    0.06
     materia
    0.06
    IEL
    0.06
    _whitespace
    0.06
    ılığı
    0.06
    CHKERRQ
    0.06
    Act Density 0.175%

    No Known Activations