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

    Neuronpedia

    INDEX
    Explanations

    each letter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कोड
    0.42
    ینہ
    0.42
     його
    0.42
    andolo
    0.41
     सन
    0.40
     аст
    0.39
     alanı
    0.39
    ceğine
    0.39
    телю
    0.38
     інші
    0.38
    POSITIVE LOGITS
     each
    1.80
     Each
    1.51
    each
    1.50
     каждого
    1.46
    Each
    1.41
     каждом
    1.41
     каждой
    1.35
     각
    1.33
     masing
    1.33
    各
    1.33
    Act Density 1.269%

    No Known Activations