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

    Neuronpedia

    INDEX
    Explanations

    Professional Certificate, continue past, request timeout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рассказал
    0.52
    ру
    0.50
    ին
    0.50
    𝓀
    0.49
     poitrine
    0.48
    িং
    0.48
     Wett
    0.48
    活用
    0.47
     каких
    0.47
     Kho
    0.47
    POSITIVE LOGITS
     absor
    0.56
     س
    0.47
    mey
    0.47
     exig
    0.46
    nger
    0.46
     و
    0.44
    na
    0.44
    lum
    0.43
    noon
    0.43
    癬
    0.42
    Act Density 0.000%

    No Known Activations