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

    Neuronpedia

    INDEX
    Explanations

    expansion and improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ni
    0.42
    1
    0.41
    ne
    0.39
    nt
    0.38
    يل
    0.38
    kl
    0.38
    kh
    0.37
    ă
    0.36
    nen
    0.35
    ires
    0.33
    POSITIVE LOGITS
    ر
    0.62
    ר
    0.49
    u
    0.46
    ar
    0.42
    ו
    0.38
    uia
    0.38
    on
    0.36
    er
    0.35
    यों
    0.35
    قوم
    0.34
    Act Density 0.740%

    No Known Activations