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

    Neuronpedia

    INDEX
    Explanations

    closing code blocks }

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    centage
    0.41
    onChange
    0.41
    阿尔
    0.39
    godic
    0.36
     Lä
    0.36
     उदाहरण
    0.36
     albo
    0.35
     veya
    0.35
     nación
    0.35
     또는
    0.35
    POSITIVE LOGITS
    <0xA6>
    0.38
    ેટ
    0.36
    愍
    0.36
    OCUS
    0.35
     gelungen
    0.35
    बता
    0.35
     partant
    0.33
     textes
    0.33
     indivíduos
    0.33
     воро
    0.32
    Act Density 0.012%

    No Known Activations