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

    Neuronpedia

    INDEX
    Explanations

    mix of languages or contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.98
    ка
    0.90
    म
    0.77
    주는
    0.75
    将
    0.73
    ната
    0.73
    んは
    0.73
     বিদেশে
    0.73
    YX
    0.71
     gives
    0.71
    POSITIVE LOGITS
    utilisateur
    0.75
    ored
    0.73
    dylib
    0.71
     perturbations
    0.70
     paroles
    0.69
     huyện
    0.69
    ultipl
    0.69
     inoculation
    0.68
     stoff
    0.68
    isticated
    0.67
    Act Density 0.000%

    No Known Activations