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

    Neuronpedia

    INDEX
    Explanations

    is usually, take by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ür
    0.44
     veramente
    0.43
     algoritmo
    0.41
     menyelesaikan
    0.40
     поля
    0.39
     ış
    0.38
     kader
    0.38
     aument
    0.38
     ампли
    0.38
    寘
    0.38
    POSITIVE LOGITS
    —
    0.43
     nonprofits
    0.43
    onc
    0.41
    banner
    0.41
     multimillion
    0.41
    த்துக்கு
    0.40
     automakers
    0.40
    ftop
    0.40
    genstein
    0.40
     neurologic
    0.40
    Act Density 0.004%

    No Known Activations