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

    Neuronpedia

    INDEX
    Explanations

    closing braces and their corresponding code structure components

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

    Non-English text

    np_acts-logits-general · gemini-2.0-flash

    string resource keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.65
    AutoScaleMode
    -0.63
    RoutingModule
    -0.60
    Geplaatst
    -0.59
    énario
    -0.54
    epar
    -0.53
     vá
    -0.53
     Herv
    -0.53
     mags
    -0.53
    τέ
    -0.53
    POSITIVE LOGITS
    <eos>
    0.90
    хьтан
    0.64
    OGND
    0.57
     ddelweddau
    0.56
     Finally
    0.53
    Enfin
    0.53
    Finally
    0.52
    endmodule
    0.52
    tanleria
    0.51
    <h2>
    0.51
    Act Density 0.220%

    No Known Activations