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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated formatting or context

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

    our possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -1.05
     MenuView
    -0.88
     الرياضيه
    -0.85
    सन्दर्भ
    -0.84
    setVerticalGroup
    -0.83
    DoubleQuotes
    -0.74
     Pristupljeno
    -0.74
     viewType
    -0.73
    posedge
    -0.71
    ="'.$
    -0.70
    POSITIVE LOGITS
    !
    0.62
     our
    0.60
    warzys
    0.51
     våre
    0.49
     we
    0.48
     nossas
    0.48
     nostra
    0.48
     spéciaux
    0.48
     наших
    0.47
     naší
    0.47
    Act Density 0.041%

    No Known Activations