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

    Neuronpedia

    INDEX
    Explanations

    negative or unfavorable conditions

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

    vis-à-vis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.55
    Numerade
    -0.54
    Izvori
    -0.54
    findpost
    -0.52
     INTERESAR
    -0.50
    KommentareTeilen
    -0.50
    providedIn
    -0.50
    Mixtures
    -0.50
    afternoon
    -0.49
     chuckles
    -0.49
    POSITIVE LOGITS
     المعيارى
    0.44
    expandindo
    0.40
     Administrativna
    0.38
    </tbody>
    0.38
    ()-
    0.35
     porcentual
    0.35
    -
    0.34
    élément
    0.34
     NUKAT
    0.33
    OrEmpty
    0.32
    Act Density 0.004%

    No Known Activations