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

    Neuronpedia

    INDEX
    Explanations

    references to data types and operations in a coding context

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

    Code and configuration file fragments

    np_acts-logits-general · gemini-2.0-flash

    foreign languages and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tonode
    -0.72
     kasarigan
    -0.66
     Forty
    -0.64
    Forty
    -0.62
     four
    -0.62
     fourth
    -0.61
    BeginInit
    -0.59
    tonsoft
    -0.59
     Four
    -0.58
     forty
    -0.58
    POSITIVE LOGITS
    0.82
    0.70
    六
    0.46
     Six
    0.45
    摘要
    0.43
     Viernes
    0.43
    <bos>
    0.43
    úncia
    0.43
    ADVERTISEMENT
    0.41
     hóspedes
    0.40
    Act Density 0.040%

    No Known Activations