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

    Neuronpedia

    INDEX
    Explanations

    audio effects or cushioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     THE
    0.51
    THE
    0.50
    ע
    0.49
    पुर
    0.45
     xwe
    0.44
    มัน
    0.40
    Man
    0.39
    위
    0.39
    JS
    0.39
     ANSWER
    0.39
    POSITIVE LOGITS
    kében
    0.56
     jurisdict
    0.49
    iping
    0.48
    朗普
    0.46
    મિંગ
    0.45
    राधिक
    0.45
    ulfonic
    0.44
     cicat
    0.44
    ipping
    0.43
     jardín
    0.43
    Act Density 0.003%

    No Known Activations