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

    Neuronpedia

    INDEX
    Explanations

    Statistical analysis in research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مخت
    -0.08
    245
    -0.07
    duce
    -0.07
    [user
    -0.06
     else
    -0.06
    natural
    -0.06
    оре
    -0.06
    alive
    -0.06
     sells
    -0.06
    ٌ
    -0.06
    POSITIVE LOGITS
     dao
    0.07
     anch
    0.07
     Copp
    0.07
     cherished
    0.06
     Fransız
    0.06
     Authorization
    0.06
     Dön
    0.06
     merciless
    0.06
     setBackgroundImage
    0.06
    Protected
    0.06
    Act Density 0.120%

    No Known Activations