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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oodoo
    -0.07
    erokee
    -0.07
    ercul
    -0.06
     cables
    -0.06
     tortured
    -0.06
    アイ
    -0.06
    عب
    -0.06
     ikinci
    -0.06
    alsa
    -0.06
    ヴ
    -0.06
    POSITIVE LOGITS
     Wal
    0.08
     slap
    0.07
     glaring
    0.07
     absence
    0.07
     працівників
    0.07
     recognizing
    0.07
     culprit
    0.07
     

↵
    0.07
     giúp
    0.07
    (Time
    0.06
    Act Density 0.017%

    No Known Activations