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

    Neuronpedia

    INDEX
    Explanations

    code syntax completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tassels
    0.31
     conifers
    0.30
    blusa
    0.29
     femora
    0.29
    ټبال
    0.29
     radially
    0.29
     outcrops
    0.29
     alkalies
    0.29
     ejaculation
    0.28
    鹸
    0.28
    POSITIVE LOGITS
    '
    0.33
    I
    0.31
    In
    0.29
    С
    0.29
    Н
    0.29
    О
    0.29
    ’
    0.29
    D
    0.28
    г
    0.28
    re
    0.27
    Act Density 0.004%

    No Known Activations