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

    Neuronpedia

    INDEX
    Explanations

    quantities of items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /Branch
    -0.09
    UCKET
    -0.09
    å³°
    -0.09
    isan
    -0.09
    yk
    -0.08
     ､
    -0.08
    /sources
    -0.08
    ê¸ī
    -0.08
    oire
    -0.08
    Coder
    -0.08
    POSITIVE LOGITS
    aceous
    0.13
     Äijai
    0.11
    ëŁī
    0.10
    melon
    0.10
    istry
    0.10
    uria
    0.10
    éĩı
    0.10
    arten
    0.10
    /png
    0.10
    stuff
    0.09
    Act Density 0.164%

    No Known Activations