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

    Neuronpedia

    INDEX
    Explanations

    frameworks, population, band types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ኼ
    0.55
     pervasive
    0.53
     علیکم
    0.52
    ลล์
    0.52
    .$.
    0.51
     പ്രവര്‍ത്തന
    0.51
     بينا
    0.51
     działa
    0.50
     maladie
    0.50
     działalności
    0.50
    POSITIVE LOGITS
    ،
    0.54
     be
    0.52
    address
    0.48
    etik
    0.46
    does
    0.45
    die
    0.45
    be
    0.45
     Also
    0.44
    有效
    0.44
    also
    0.43
    Act Density 0.000%

    No Known Activations