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

    Neuronpedia

    INDEX
    Explanations

    remove, adjust, or control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     electrónica
    0.48
     ilustración
    0.47
     ос
    0.46
     रिपीट
    0.46
     مليون
    0.45
     жен
    0.44
     рит
    0.44
     reproduced
    0.43
     বন
    0.43
     периода
    0.43
    POSITIVE LOGITS
    ợi
    0.45
    നാള
    0.45
    하나
    0.45
    ковы
    0.45
    ค่ะ
    0.44
    때
    0.44
    들과
    0.43
    opaque
    0.43
    चा
    0.42
    及び
    0.42
    Act Density 0.004%

    No Known Activations