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

    Neuronpedia

    INDEX
    Explanations

    itself, themselves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.63
     and
    0.57
     feces
    0.55
     but
    0.54
     pero
    0.52
    اؤ
    0.52
     và
    0.51
     dari
    0.50
     که
    0.50
     perceive
    0.49
    POSITIVE LOGITS
    本身
    0.50
    黢
    0.47
     itself
    0.46
    许多
    0.44
    เอง
    0.44
     자체가
    0.44
     자체
    0.44
    स्
    0.44
    重新
    0.44
    自身
    0.43
    Act Density 0.007%

    No Known Activations