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

    Neuronpedia

    INDEX
    Explanations

    bolded phrases and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.57
    ()
    0.52
    0
    0.48
    ET
    0.46
    AB
    0.46
    Bindings
    0.45
     fossa
    0.44
    IO
    0.44
    HTML
    0.44
    +
    0.44
    POSITIVE LOGITS
    ↵
    0.66
    کسی
    0.49
     जबरदस्त
    0.46
     ።
    0.46
    ın
    0.46
    在我们
    0.46
    mě
    0.45
    น
    0.45
    ൈ
    0.45
    ↵↵↵↵
    0.44
    Act Density 0.649%

    No Known Activations