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

    Neuronpedia

    INDEX
    Explanations

    hormones, genocide, methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    рур
    0.46
    ᒻ
    0.44
     алгорит
    0.44
    ן
    0.44
     almond
    0.43
     രജി
    0.43
    ⨔
    0.43
    ODBA
    0.42
    CHREIB
    0.41
     mengubah
    0.41
    POSITIVE LOGITS
     in
    0.52
    es
    0.51
     with
    0.49
    is
    0.47
    tt
    0.47
    ve
    0.46
    il
    0.46
    nt
    0.46
     Cook
    0.46
    ato
    0.45
    Act Density 0.001%

    No Known Activations