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

    Neuronpedia

    INDEX
    Explanations

    characters and special symbols used in programming or scripting languages

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

    <start_of_turn> text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plazos
    -0.38
     Apare
    -0.35
     rivales
    -0.34
     lazos
    -0.34
    ตก
    -0.33
    xtick
    -0.33
     ámbitos
    -0.33
     plata
    -0.33
     sabiduría
    -0.31
     ympä
    -0.31
    POSITIVE LOGITS
    haikusbot
    0.63
    AccessorTable
    0.59
    存于互联网档案馆
    0.57
     محفوظة
    0.56
    extAlignment
    0.56
    
    0.51
    msgTypes
    0.50
    TabIndex
    0.50
    UnsafeEnabled
    0.50
    GTCX
    0.50
    Act Density 0.004%

    No Known Activations