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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax and structure elements

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

    numerical sequences or code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.82
     المعيارى
    -0.73
    enumii
    -0.69
    ſſung
    -0.69
    Datuak
    -0.68
    <pad>
    -0.67
    ſicht
    -0.66
    <unused52>
    -0.66
    <unused17>
    -0.66
    <unused3>
    -0.66
    POSITIVE LOGITS
    0
    0.43
     manuales
    0.38
     pauvre
    0.36
     hasard
    0.35
     manuell
    0.35
     artificiales
    0.35
     Contoh
    0.35
     desconocido
    0.34
     financieras
    0.34
     inmediatamente
    0.33
    Act Density 0.047%

    No Known Activations