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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpreting and analyzing data

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

    interpretation of data or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ConstraintMaker
    -0.59
    جوايز
    -0.54
    RenderAtEndOf
    -0.47
    PyExc
    -0.47
    modb
    -0.46
     olympiques
    -0.44
     surla
    -0.44
     enfans
    -0.44
    المناصب
    -0.43
     prawda
    -0.42
    POSITIVE LOGITS
     interpretation
    1.39
     interpret
    1.38
     interpreting
    1.34
     INTERPRET
    1.29
     interpreted
    1.28
     Interpre
    1.27
     Interpretation
    1.26
     interprets
    1.26
     interpretar
    1.25
    Interpret
    1.25
    Act Density 0.042%

    No Known Activations