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

    Neuronpedia

    INDEX
    Explanations

    variable declarations in programming contexts

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

    variable assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.79
    Personendaten
    -0.78
    awtextra
    -0.78
    UnusedPrivate
    -0.78
    SequentialGroup
    -0.77
    makeConstraints
    -0.76
     transfieras
    -0.75
     utafitiHapana
    -0.75
     propOrder
    -0.74
    tagHelperRunner
    -0.73
    POSITIVE LOGITS
    ↵
    0.32
     are
    0.29
     dam
    0.28
     (
    0.28
    ,
    0.27
     posibilidad
    0.27
     causes
    0.26
    .
    0.26
     do
    0.26
     .
    0.26
    Act Density 0.185%

    No Known Activations