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

    Neuronpedia

    INDEX
    Explanations

    signals and slots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ആ
    0.49
    لك
    0.48
    ခင်
    0.46
     decisione
    0.46
    อร์
    0.45
     pien
    0.45
     Car
    0.44
     elektr
    0.44
     HCl
    0.44
     lunchtime
    0.44
    POSITIVE LOGITS
    ronym
    0.53
    मपुर
    0.50
    why
    0.49
    espoir
    0.49
    animation
    0.47
    ו
    0.47
    ۵
    0.47
    substr
    0.47
    ufer
    0.47
    inander
    0.46
    Act Density 0.000%

    No Known Activations