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

    Neuronpedia

    INDEX
    Explanations

    Hence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    едера
    -0.07
     TextView
    -0.07
     hơn
    -0.07
    toBeTruthy
    -0.07
     Okay
    -0.06
     superst
    -0.06
     schwer
    -0.06
    -gray
    -0.06
     تاب
    -0.06
     *"
    -0.06
    POSITIVE LOGITS
     Hence
    0.09
    unge
    0.07
     engagement
    0.07
     leverage
    0.07
    网刊
    0.07
     hence
    0.06
     rationale
    0.06
     bande
    0.06
     pute
    0.06
     hose
    0.06
    Act Density 0.004%

    No Known Activations