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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    identity
    0.41
    format
    0.41
    vod
    0.39
    neg
    0.39
    bar
    0.38
     कोणत्या
    0.38
    tern
    0.37
    frac
    0.37
    road
    0.37
    ién
    0.37
    POSITIVE LOGITS
    MaxPooling
    0.46
     максима
    0.45
     maximise
    0.44
     максимально
    0.44
     maximizes
    0.44
     макси
    0.43
     wealthiest
    0.41
    ഔ
    0.40
    кове
    0.40
    最后的
    0.40
    Act Density 0.001%

    No Known Activations