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

    Neuronpedia

    INDEX
    Explanations

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    तुरंग
    0.38
    ربون
    0.38
     பிச்சு
    0.38
    لوم
    0.37
    ლის
    0.37
    ২৬
    0.37
     goomba
    0.37
     copyspace
    0.36
     tölt
    0.36
    faulse
    0.36
    POSITIVE LOGITS
     et
    0.86
     and
    0.67
     &
    0.62
     ও
    0.52
    ,
    0.52
    &
    0.49
     и
    0.48
     J
    0.46
     và
    0.45
    and
    0.43
    Act Density 0.004%

    No Known Activations