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

    Neuronpedia

    INDEX
    Explanations

    lines blur

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㓦
    0.41
     پس
    0.40
     HSE
    0.37
     bawang
    0.37
    Ⲑ
    0.37
    UnderTest
    0.37
     tật
    0.37
     ধর্ষণ
    0.37
    rombin
    0.36
     pavilions
    0.36
    POSITIVE LOGITS
     kaya
    0.37
     won
    0.36
    스테
    0.36
    お待ち
    0.36
     Wyd
    0.35
    inter
    0.35
    apart
    0.35
     Blur
    0.35
     opaque
    0.35
     haze
    0.34
    Act Density 0.000%

    No Known Activations