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

    Neuronpedia

    INDEX
    Explanations

    open source

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    కు
    0.74
    בר
    0.71
     Universidade
    0.65
     янва
    0.62
    лдуу
    0.62
    viridis
    0.61
    TODO
    0.61
    nuxt
    0.61
     (_,
    0.61
    لې
    0.61
    POSITIVE LOGITS
    in
    0.80
    ه
    0.76
    a
    0.73
    ische
    0.71
     not
    0.70
    ší
    0.68
     spezielle
    0.68
     off
    0.67
    的方式
    0.67
    cción
    0.66
    Act Density 0.011%

    No Known Activations