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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements and quantities related to chemical properties and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Units or measurements

    np_acts-logits-general · gemini-2.0-flash

    inverse units or rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dis
    -0.73
     Dis
    -0.72
     disturbed
    -0.67
     DIST
    -0.66
    dis
    -0.65
     disturb
    -0.64
     Dist
    -0.64
     dis
    -0.64
     disrupt
    -0.63
    URLException
    -0.63
    POSITIVE LOGITS
    ^{-
    1.34
    }^{-
    1.32
    ]^{-
    1.22
     inverse
    1.19
    )^{-
    1.18
     }^{-
    1.13
     ^{-
    1.11
    inverse
    1.03
    Inverse
    0.97
     Inverse
    0.97
    Act Density 0.637%

    No Known Activations