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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate assessment or judgment, particularly related to legality and performance

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

    situational assessments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -1.05
    LookAnd
    -0.69
     noDo
    -0.68
    ⓧ
    -0.66
    GraphicsUnit
    -0.65
     للمعارف
    -0.65
    UnknownFieldSet
    -0.64
    нгред
    -0.63
    Bibitem
    -0.63
    principalColumn
    -0.61
    POSITIVE LOGITS
     too
    0.44
    っこ
    0.36
     Lee
    0.35
    eri
    0.35
     sin
    0.35
     E
    0.34
    ,
    0.34
     Sin
    0.33
    ak
    0.32
     wall
    0.32
    Act Density 0.433%

    No Known Activations