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

    Neuronpedia

    INDEX
    Explanations

    manual method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.61
     pals
    0.52
     sax
    0.51
     aktual
    0.50
    Thought
    0.49
    ww
    0.48
     frm
    0.48
     ocasión
    0.48
     ¥
    0.48
    llvm
    0.48
    POSITIVE LOGITS
    ก
    0.62
    ક
    0.59
    ك
    0.56
    ू
    0.53
    كَ
    0.52
    프
    0.51
    크
    0.50
    ক
    0.50
    드
    0.50
    ्य
    0.49
    Act Density 0.001%

    No Known Activations