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

    Neuronpedia

    INDEX
    Explanations

    statements about persistence and repeated actions

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

    proved again and again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.56
    CppCodeGen
    -0.50
    żesz
    -0.49
    msgTypes
    -0.40
    writeFieldEnd
    -0.40
     defaultstate
    -0.40
    transQ
    -0.39
     fresa
    -0.38
    RenderAtEndOf
    -0.38
    __*/
    -0.37
    POSITIVE LOGITS
     proves
    0.60
     vermogen
    0.54
     demuestra
    0.54
     membuk
    0.53
    ChildScrollView
    0.52
     prouve
    0.51
     Beweis
    0.50
     demonstrates
    0.50
     Proving
    0.50
     prove
    0.48
    Act Density 0.051%

    No Known Activations