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

    Neuronpedia

    INDEX
    Explanations

    pre minus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     실행
    0.27
     작성
    0.26
     yatırım
    0.26
     투자
    0.26
     확률
    0.25
     kinematic
    0.25
     что
    0.24
    投资
    0.24
     ی
    0.24
     delectable
    0.24
    POSITIVE LOGITS
    ls
    0.29
    ਲਾ
    0.26
    icl
    0.26
    âmara
    0.25
    apons
    0.25
    lv
    0.24
    agence
    0.24
    requent
    0.24
    á
    0.23
    ala
    0.23
    Act Density 0.000%

    No Known Activations