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

    Neuronpedia

    INDEX
    Explanations

    xargs commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     मुख
    0.45
     ब्ल
    0.44
    shr
    0.43
     Controlled
    0.42
     पाती
    0.42
     બ્
    0.41
    竑
    0.40
    rogenic
    0.40
    IELD
    0.39
     concealment
    0.39
    POSITIVE LOGITS
    osk
    0.41
     x
    0.41
    args
    0.39
    ł
    0.38
    ilos
    0.36
    Act
    0.35
    स्पर
    0.35
    yl
    0.35
    Args
    0.35
    ifters
    0.35
    Act Density 0.004%

    No Known Activations