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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight an increase or greater degree in various contexts

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

    more than X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.71
    principalColumn
    -0.69
    erintah
    -0.58
     OMIT
    -0.57
    WithMany
    -0.56
    [@BOS@]
    -0.56
     BoxFit
    -0.56
    BibitemShut
    -0.56
    <unused41>
    -0.56
     Signalez
    -0.56
    POSITIVE LOGITS
    net
    0.29
    pidou
    0.26
     jed
    0.25
    打
    0.25
    apimachinery
    0.25
    max
    0.24
    Mara
    0.23
    Tra
    0.23
     
    0.23
    Circle
    0.23
    Act Density 0.074%

    No Known Activations