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

    Neuronpedia

    INDEX
    Explanations

    architectural features and significant structures

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

    curved glass facade and twisting shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    athread
    -0.40
     Kälte
    -0.40
     pageContext
    -0.37
    ometra
    -0.37
    انيف
    -0.36
     smrti
    -0.35
    ioutil
    -0.35
    gjenge
    -0.35
     mía
    -0.34
    +};
    -0.34
    POSITIVE LOGITS
    ⤹
    0.48
    endmodule
    0.47
     disambiguazione
    0.47
     twisting
    0.46
    ParallelGroup
    0.46
     pulse
    0.46
    扭曲
    0.46
     curving
    0.46
    stylers
    0.46
    InitVars
    0.45
    Act Density 0.029%

    No Known Activations