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

    Neuronpedia

    INDEX
    Explanations

    start of common terms like async, sophisticated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CUT
    0.56
     front
    0.51
    letto
    0.50
    场
    0.50
    kten
    0.49
    stock
    0.49
    cle
    0.49
     нема
    0.48
    not
    0.47
     έχ
    0.47
    POSITIVE LOGITS
    Isra
    0.78
    ⓑ
    0.77
    spider
    0.75
     അമേ
    0.74
    ኘ
    0.72
    ुलेंस
    0.72
    urrection
    0.71
    izieren
    0.71
    Agregar
    0.70
    唿
    0.70
    Act Density 0.190%

    No Known Activations