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

    Neuronpedia

    INDEX
    Explanations

    api routes and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.66
     कार
    0.57
     โดย
    0.56
     .
    0.56
     ket
    0.56
     b
    0.54
     for
    0.54
    ACT
    0.54
    𝐼
    0.53
    िंग
    0.52
    POSITIVE LOGITS
    ור
    0.73
    ви
    0.69
    рот
    0.64
     Calyce
    0.62
    ચ્
    0.61
    elbe
    0.61
    চ্
    0.60
    રો
    0.59
     اكثر
    0.59
     ро
    0.58
    Act Density 0.003%

    No Known Activations