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

    Neuronpedia

    INDEX
    Explanations

    pend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     updateUser
    -0.08
     xuân
    -0.07
     jealousy
    -0.07
     admins
    -0.07
    Toast
    -0.07
    ᴼ
    -0.07
    кс
    -0.07
    ଓ
    -0.07
     checkbox
    -0.07
     improve
    -0.07
    POSITIVE LOGITS
    🐓
    0.07
    .Fatalf
    0.07
     som
    0.07
     stem
    0.07
    缒
    0.07
    menu
    0.07
    Negative
    0.07
    ={[
    0.06
    盘
    0.06
     một
    0.06
    Act Density 0.003%

    No Known Activations