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

    Neuronpedia

    INDEX
    Explanations

    handling correctly, semantic understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quadrant
    0.39
    witter
    0.36
     hark
    0.36
    旅遊
    0.35
    Questa
    0.35
    敦
    0.35
     orchestration
    0.35
     legs
    0.35
     Marquette
    0.34
    lardır
    0.34
    POSITIVE LOGITS
    Oil
    0.41
    الو
    0.41
    itou
    0.40
     Annotated
    0.40
    setConfig
    0.40
    Polynomial
    0.40
     significativas
    0.40
     Oil
    0.38
     setName
    0.38
     Worm
    0.38
    Act Density 0.001%

    No Known Activations