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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to engineering and manufacturing processes

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

    Follows "same", "in", or a length measurement

    np_acts-logits-general · gemini-2.0-flash

    same or whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.51
    /*!
    -0.45
     typelib
    -0.44
    //
    -0.43
    RegressionTest
    -0.42
     חיצוניים
    -0.40
    AsUp
    -0.40
    IContainer
    -0.40
     postales
    -0.40
    IconModule
    -0.39
    POSITIVE LOGITS
     whatever
    0.90
     whichever
    0.84
    whatever
    0.82
     Whatever
    0.82
    Whatever
    0.81
     wherever
    0.65
     kasarigan
    0.62
     whome
    0.57
     выбран
    0.56
     whoever
    0.56
    Act Density 1.073%

    No Known Activations