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

    Neuronpedia

    INDEX
    Explanations

    student experiences and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.54
     waktu
    1.52
     बाप
    1.50
     społecz
    1.49
     gern
    1.48
    вате
    1.48
    선을
    1.47
     постара
    1.47
    ্ড
    1.46
    魎
    1.46
    POSITIVE LOGITS
    le
    1.79
    ار
    1.67
    t
    1.58
    marg
    1.56
    or
    1.51
    𝑙
    1.50
    j
    1.46
    inin
    1.43
    alg
    1.40
    era
    1.36
    Act Density 0.030%

    No Known Activations