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

    Neuronpedia

    INDEX
    Explanations

    various numerical representations, particularly focusing on negative and positive integer values

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.53
     igenom
    -0.51
    exitRule
    -0.47
    WebVitals
    -0.45
     TType
    -0.41
     &___
    -0.40
     wzglę
    -0.40
    EndGlobalSection
    -0.40
    abbix
    -0.40
    redund
    -0.39
    POSITIVE LOGITS
    UrlResolution
    0.41
    richTextPanel
    0.39
     commonwealth
    0.39
     doughnut
    0.38
    addGap
    0.38
    +"'
    0.37
    bola
    0.37
     weekend
    0.36
    গ্রহ
    0.36
    umina
    0.36
    Act Density 0.144%

    No Known Activations