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

    Neuronpedia

    INDEX
    Explanations

    runtime and CYP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cargar
    0.39
    geme
    0.38
     convencional
    0.37
     ნახ
    0.37
     আগ
    0.37
     सिक्स
    0.37
     arraigned
    0.37
     elog
    0.36
    ingi
    0.36
     hogares
    0.36
    POSITIVE LOGITS
    native
    0.46
    natives
    0.45
    Native
    0.44
     native
    0.41
    CSS
    0.40
    資
    0.39
    content
    0.37
     hygiene
    0.37
    icons
    0.37
    ⸩
    0.37
    Act Density 0.000%

    No Known Activations