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

    Neuronpedia

    INDEX
    Explanations

    finding a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.64
    ين
    0.52
     Molding
    0.48
     hides
    0.48
     levando
    0.46
    erving
    0.45
    ري
    0.44
    "
    0.42
     covers
    0.42
    时候
    0.42
    POSITIVE LOGITS
    gruppe
    0.57
    ﺎ
    0.55
    gruppen
    0.54
    𝕒
    0.50
    үүн
    0.48
    aient
    0.47
     した
    0.47
    aż
    0.46
    ле
    0.46
    ్
    0.45
    Act Density 0.292%

    No Known Activations