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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols used in programming code

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

    android code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cumplido
    -0.49
    \{\\
    -0.49
     escuchado
    -0.49
     afectadas
    -0.48
     venido
    -0.48
     jugado
    -0.47
     detenido
    -0.46
     llorar
    -0.46
    épaisseur
    -0.45
     isolada
    -0.45
    POSITIVE LOGITS
     NSCoder
    0.52
     ?";
    0.47
    SBATCH
    0.47
    SequentialGroup
    0.46
    Хьажоргаш
    0.44
    RTEX
    0.43
    GTCX
    0.43
    DNN
    0.43
    Clik
    0.42
    WEBPACK
    0.41
    Act Density 0.008%

    No Known Activations