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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    taking
    0.52
    Тем
    0.52
    array
    0.51
    हिले
    0.50
    摂
    0.50
    োহ
    0.49
    ્યાં
    0.49
    線性
    0.48
    taker
    0.48
    ণ্ডল
    0.48
    POSITIVE LOGITS
     till
    0.63
     рядом
    0.62
     पिछली
    0.61
    ઁ
    0.61
     Across
    0.61
     μέχρι
    0.60
     சர்
    0.59
    ibouti
    0.59
     across
    0.58
     glad
    0.58
    Act Density 0.000%

    No Known Activations