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

    Neuronpedia

    INDEX
    Explanations

    misinformation and income

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Noida
    0.49
     wydar
    0.47
     Kowloon
    0.46
    ޯ
    0.45
    ാന
    0.45
    O
    0.45
    0.45
     특징
    0.44
    writeFile
    0.44
     excerpts
    0.44
    POSITIVE LOGITS
    glucose
    0.50
     mdl
    0.49
     gas
    0.48
     ka
    0.48
     necess
    0.47
     бо
    0.47
     gg
    0.46
     ki
    0.46
    glie
    0.46
     na
    0.46
    Act Density 0.000%

    No Known Activations