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

    Neuronpedia

    INDEX
    Explanations

    http and www links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atal
    0.72
    colas
    0.69
    ール
    0.69
    microsoft
    0.69
    amba
    0.69
     Kiran
    0.68
     Yale
    0.68
    irt
    0.68
    Bul
    0.67
    gang
    0.67
    POSITIVE LOGITS
    www
    0.86
     www
    0.77
     http
    0.69
     (€
    0.67
     turmeric
    0.65
     tacky
    0.65
    條件
    0.65
    ❍
    0.64
     complicated
    0.64
    图案
    0.63
    Act Density 0.065%

    No Known Activations