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

    Neuronpedia

    INDEX
    Explanations

    welcome change / respite / relief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ler
    0.29
    ring
    0.29
     symmetric
    0.29
    leri
    0.28
     समार
    0.27
    ise
    0.27
    lor
    0.26
    mert
    0.26
     syrups
    0.26
     kembali
    0.26
    POSITIVE LOGITS
    क
    0.28
    ле
    0.27
    ਨ
    0.26
     cuyas
    0.26
    ма
    0.26
    нула
    0.25
    новниш
    0.25
    φα
    0.25
    اني
    0.24
    лия
    0.24
    Act Density 0.001%

    No Known Activations