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

    Neuronpedia

    INDEX
    Explanations

    requests

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *
    0.49
    <eos>
    0.48
     later
    0.46
     even
    0.46
    在其
    0.45
     –
    0.43
     */
    0.43
    Later
    0.43
     _
    0.42
     Later
    0.41
    POSITIVE LOGITS
     poesia
    0.67
     atualização
    0.66
     riforma
    0.66
    おすすめ
    0.65
     cmake
    0.65
     recomendaciones
    0.63
     scrivere
    0.63
     یہودیوں
    0.63
     brasileiros
    0.63
     recomand
    0.63
    Act Density 1.238%

    No Known Activations