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

    Neuronpedia

    INDEX
    Explanations

    terms related to media type validation and content acceptance

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

    allowed, possible, supported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Выводы
    -0.35
    HttpPost
    -0.34
    RunWith
    -0.34
     magát
    -0.33
     voet
    -0.33
     calça
    -0.33
    Заключение
    -0.33
    Спољашње
    -0.33
     itself
    -0.32
     fallu
    -0.31
    POSITIVE LOGITS
    EDEFAULT
    0.75
     possibles
    0.70
     permissible
    0.69
     admissible
    0.66
    possible
    0.63
     allowable
    0.62
    Possible
    0.62
    eligible
    0.61
    candidate
    0.60
     candidates
    0.59
    Act Density 0.105%

    No Known Activations