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

    Neuronpedia

    INDEX
    Explanations

    setopt and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     വിവിധ
    0.46
    ፦
    0.42
    셧
    0.42
     vudd
    0.41
    𒊕
    0.40
    <unused40>
    0.39
    Eppo
    0.39
     समीप
    0.39
     kammam
    0.39
     नै
    0.38
    POSITIVE LOGITS
    ↵
    0.46
    alı
    0.41
    green
    0.41
     "
    0.40
    ear
    0.40
    gen
    0.39
    all
    0.39
    0.39
    ...
    0.39
    enc
    0.38
    Act Density 0.018%

    No Known Activations