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

    Neuronpedia

    INDEX
    Explanations

    css properties ending in semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    奋斗
    0.39
    enheim
    0.37
    byshire
    0.37
    lengths
    0.36
    omod
    0.35
    anthem
    0.35
    ignan
    0.35
    තාව
    0.34
    forces
    0.34
    ในช่วง
    0.34
    POSITIVE LOGITS
     consecuencia
    0.42
     descent
    0.39
    ͅ
    0.39
     खुदाई
    0.38
    ANCIS
    0.37
     Descent
    0.37
    ੱਚ
    0.36
    咔
    0.36
    ולנד
    0.36
     ô
    0.36
    Act Density 0.001%

    No Known Activations