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

    Neuronpedia

    INDEX
    Explanations

    lists, separators, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bitmaps
    0.29
    萜
    0.28
     embro
    0.27
     വിവര
    0.27
    😧
    0.27
     démon
    0.27
    黢
    0.26
     weaknesses
    0.26
     proteinuria
    0.26
     îm
    0.26
    POSITIVE LOGITS
    7
    0.41
    .
    0.40
    4
    0.39
    5
    0.39
    6
    0.36
    8
    0.34
    ный
    0.33
    ig
    0.32
    aji
    0.30
    3
    0.30
    Act Density 0.152%

    No Known Activations