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

    Neuronpedia

    INDEX
    Explanations

    code elements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وليس
    0.81
     počet
    0.74
     nhiên
    0.73
     dasar
    0.71
    straction
    0.71
    ॉजी
    0.70
     বিল্ডিং
    0.70
    蒲
    0.68
     ث
    0.68
     ço
    0.68
    POSITIVE LOGITS
    oll
    0.81
    osso
    0.76
    ulata
    0.76
    olle
    0.75
    inato
    0.72
    -...
    0.72
    isotopes
    0.71
    riff
    0.69
    isotope
    0.69
    olive
    0.67
    Act Density 0.000%

    No Known Activations