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

    Neuronpedia

    INDEX
    Explanations

    say "g" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تمتع
    -0.08
    𬬱
    -0.07
     может
    -0.07
    𬞟
    -0.07
    )();↵
    -0.07
    evity
    -0.07
    גורמים
    -0.07
    ━━
    -0.07
    ㈔
    -0.07
     UIEdgeInsets
    -0.06
    POSITIVE LOGITS
    (named
    0.07
     UserControl
    0.07
    𝐍
    0.07
     Hotel
    0.07
    .beh
    0.07
    _BO
    0.07
    Sm
    0.07
     NY
    0.07
    ashes
    0.07
     Beckham
    0.07
    Act Density 0.006%

    No Known Activations