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

    Neuronpedia

    INDEX
    Explanations

    technical terms and coding structures related to object encoding and decoding processes

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

    encoding data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.79
    HtmlAttribute
    -0.77
     ब्रेकडाउन
    -0.66
     <=",
    -0.65
    intios
    -0.64
    SBATCH
    -0.61
    ManagedBean
    -0.60
     MainAxisSize
    -0.60
    AsUp
    -0.59
     للمعارف
    -0.58
    POSITIVE LOGITS
     encoding
    0.90
    encode
    0.88
    Encode
    0.84
     Encode
    0.83
     encode
    0.83
     Encoding
    0.82
    encoding
    0.79
     coding
    0.79
    Encoding
    0.75
    Encoder
    0.74
    Act Density 0.044%

    No Known Activations