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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Minus
    -0.06
     rankings
    -0.06
    ılmış
    -0.06
     Expert
    -0.06
    ヴ
    -0.06
     되어
    -0.06
     ACLU
    -0.06
     компанії
    -0.06
     بسبب
    -0.06
     Engineers
    -0.06
    POSITIVE LOGITS
    _MEDIA
    0.07
     dealing
    0.07
     stash
    0.07
    _BITMAP
    0.06
    usiness
    0.06
     조선
    0.06
    /Object
    0.06
     gönder
    0.06
     setDate
    0.06
    ")+
    0.06
    Act Density 0.025%

    No Known Activations