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

    Neuronpedia

    INDEX
    Explanations

    code imports and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नहीं
    0.40
     toast
    0.39
     obscure
    0.39
     neutrals
    0.39
     circumst
    0.38
     numeral
    0.38
     overwhelm
    0.38
     background
    0.37
    বেশী
    0.37
     hash
    0.37
    POSITIVE LOGITS
    ન
    0.52
    Б
    0.51
    Ра
    0.46
    Р
    0.45
    પ
    0.45
     лист
    0.44
    कंप
    0.44
     الك
    0.44
    બ
    0.44
     включая
    0.43
    Act Density 0.012%

    No Known Activations