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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or references to similar items or concepts

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

    such as examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.38
     scre
    -0.38
    фик
    -0.36
    Personensuche
    -0.35
     qed
    -0.35
     Rukh
    -0.35
    acheco
    -0.34
     Inet
    -0.34
     Hez
    -0.34
     couleur
    -0.34
    POSITIVE LOGITS
     including
    0.77
     Including
    0.73
    Including
    0.73
     såsom
    0.70
     INCLUDING
    0.69
     kuten
    0.69
     zoals
    0.66
     waaronder
    0.66
    including
    0.66
     incluyendo
    0.65
    Act Density 0.203%

    No Known Activations