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

    Neuronpedia

    INDEX
    Explanations

    equality and assignment operators

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

    The equals sign

    np_acts-logits-general · gemini-2.0-flash

    equals sign usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     архивлан
    -0.63
    DebuggerNonUser
    -0.62
    tagHelperRunner
    -0.59
    Становништво
    -0.58
    selbe
    -0.56
    -
    -0.54
    Slides
    -0.53
    ous
    -0.53
    kirch
    -0.52
     study
    -0.51
    POSITIVE LOGITS
    /=
    1.54
    /−
    0.89
    ++++++++
    0.85
     CreateTagHelper
    0.82
    _=
    0.82
    ++++++++++++++++
    0.81
    .=
    0.79
    :=
    0.74
    hitheatre
    0.74
     مرئيه
    0.72
    Act Density 0.446%

    No Known Activations