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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and variables within a code context

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

    variable assignment and creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.69
    principalTable
    -0.67
    ]")]
    -0.59
    UVWXYZ
    -0.57
    ſelves
    -0.57
     SRA
    -0.56
     myſelf
    -0.56
    RTGC
    -0.55
    ſelf
    -0.54
    rinth
    -0.54
    POSITIVE LOGITS
     bambú
    0.41
     herinner
    0.40
     impreso
    0.40
     verificación
    0.40
     elegancia
    0.40
     exhibición
    0.39
     fieltro
    0.39
     astore
    0.39
     Moscú
    0.39
     læng
    0.38
    Act Density 0.049%

    No Known Activations