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

    Neuronpedia

    INDEX
    Explanations

    terminology related to critical reviews or assessments

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

    crit or −/−

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.56
    NgModule
    -0.49
     säga
    -0.47
    multer
    -0.44
     utafitiHapana
    -0.43
    WebpackPlugin
    -0.43
     seguente
    -0.43
    ệc
    -0.42
     sayfa
    -0.42
    もちゃ
    -0.42
    POSITIVE LOGITS
     Crit
    2.16
    Crit
    2.13
     crit
    2.13
    crit
    2.00
     critters
    1.56
    critical
    1.14
     critical
    1.11
     Critical
    1.05
    Critical
    1.05
     CRITICAL
    0.93
    Act Density 0.003%

    No Known Activations