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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one."

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

    one of the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     religión
    -0.35
     fría
    -0.35
     gesamten
    -0.35
     siguiente
    -0.33
     gesamte
    -0.32
     volcán
    -0.32
     Völker
    -0.31
     ejecutivo
    -0.31
     profesión
    -0.31
     Incluye
    -0.30
    POSITIVE LOGITS
    MENAFN
    0.84
     nahilalakip
    0.73
     يتيمه
    0.73
     nakalista
    0.71
     ब्रेकडाउन
    0.67
     informée
    0.67
    webElement
    0.66
    archiviato
    0.66
     nonUne
    0.65
    makeConstraints
    0.65
    Act Density 0.040%

    No Known Activations