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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '=>['
    -0.06
     dia
    -0.06
     twisted
    -0.06
     averaging
    -0.06
     bureau
    -0.06
     wash
    -0.06
    VERBOSE
    -0.06
     paragraph
    -0.06
     OVERRIDE
    -0.06
     Occupation
    -0.06
    POSITIVE LOGITS
    ’ın
    0.07
    وم
    0.07
    ήν
    0.07
     Ev
    0.06
    olina
    0.06
    -я
    0.06
    žitě
    0.06
     �
    0.06
    _Price
    0.06
    مانی
    0.06
    Act Density 0.004%

    No Known Activations