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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posium
    -0.07
     Zus
    -0.06
    _Off
    -0.06
    Evaluator
    -0.06
    ueblo
    -0.06
    くん
    -0.06
    .VAL
    -0.06
    consin
    -0.06
     ناب
    -0.06
    Should
    -0.05
    POSITIVE LOGITS
     BigInteger
    0.07
    .ALL
    0.07
    Noise
    0.07
    Only
    0.07
    make
    0.07
    ounced
    0.07
    %);↵
    0.06
     sixty
    0.06
     bear
    0.06
     turkey
    0.06
    Act Density 0.008%

    No Known Activations