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

    Neuronpedia

    INDEX
    Explanations

    words related to experiments, especially related to the body or government

    oai_token-act-pair · gemini-2.0-flash

    scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.93
    numerusform
    -0.79
    adaptiveStyles
    -0.79
    principalColumn
    -0.78
     كومونز
    -0.75
    ंदीखरीदारी
    -0.73
     Efq
    -0.72
     contextLoads
    -0.71
    ]")]
    -0.67
    gbaar
    -0.67
    POSITIVE LOGITS
    A
    0.43
     (
    0.42
    M
    0.41
     
    0.40
     [
    0.40
     bocas
    0.39
    highlight
    0.38
    O
    0.38
    ↵↵
    0.38
     respectivamente
    0.37
    Act Density 0.548%

    No Known Activations