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

    Neuronpedia

    INDEX
    Explanations

    import from '

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ARY
    0.41
    ICATION
    0.40
    сона
    0.38
    IANA
    0.37
     habitaciones
    0.36
    IA
    0.36
    ERV
    0.36
     filer
    0.35
    IAC
    0.34
    INE
    0.34
    POSITIVE LOGITS
    s
    0.54
    都
    0.48
    ă
    0.48
    ä
    0.47
    の
    0.46
    ों
    0.43
    २
    0.41
    澜
    0.40
    ის
    0.40
    と
    0.40
    Act Density 0.008%

    No Known Activations