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

    Neuronpedia

    INDEX
    Explanations

    important note disease trespassing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Painting
    0.44
     Mae
    0.44
     Ayo
    0.42
     Tse
    0.41
    าว
    0.41
    Painting
    0.39
    മിക
    0.39
     பகுதியில்
    0.39
     Aux
    0.38
     Yin
    0.38
    POSITIVE LOGITS
     vó
    0.41
     consideration
    0.39
     actualización
    0.38
     passions
    0.37
     understanding
    0.36
    resolve
    0.36
     kov
    0.36
     favourite
    0.35
     crocodile
    0.35
    ळं
    0.35
    Act Density 0.001%

    No Known Activations