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

    Neuronpedia

    INDEX
    Explanations

    the word "only."

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

    can only Verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plazos
    -0.46
     avoient
    -0.46
    ambién
    -0.43
     fuis
    -0.42
     Adolfo
    -0.42
     věci
    -0.42
     informaciones
    -0.41
     Familienname
    -0.41
     Kartoffeln
    -0.41
     dorados
    -0.41
    POSITIVE LOGITS
    只能
    0.75
     Cannot
    0.68
    Cannot
    0.66
    也只能
    0.65
    basicConfig
    0.63
    cannot
    0.61
     cannot
    0.61
     CANNOT
    0.59
    Must
    0.58
    DMETHOD
    0.56
    Act Density 0.005%

    No Known Activations