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

    Neuronpedia

    INDEX
    Explanations

    references to screens in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    screens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InteropServices
    -0.50
     Kaufman
    -0.41
    </i>
    -0.38
     Von
    -0.37
    groupBox
    -0.35
    </sub>
    -0.35
     Byrd
    -0.35
     Junge
    -0.35
     York
    -0.35
    ↵↵↵
    -0.34
    POSITIVE LOGITS
    screens
    2.03
    Screens
    1.55
     Screens
    1.35
     screens
    1.30
    creens
    1.07
     pantallas
    0.98
     écrans
    0.82
     HomeScreen
    0.77
     increí
    0.66
     bershka
    0.64
    Act Density 0.001%

    No Known Activations