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

    Neuronpedia

    INDEX
    Explanations

    diverse subjects

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ходят
    0.70
    敔
    0.68
    вания
    0.66
    ,\,\,\,\
    0.62
     ليست
    0.61
    лил
    0.61
    enciais
    0.61
     wówczas
    0.61
     వాహ
    0.60
    ટી
    0.60
    POSITIVE LOGITS
     ELECTRO
    0.63
    abank
    0.62
    康
    0.61
     swims
    0.60
     electro
    0.59
     severe
    0.59
    耱
    0.57
    radas
    0.57
    லோச
    0.57
     reconstruction
    0.57
    Act Density 0.000%

    No Known Activations