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

    Neuronpedia

    INDEX
    Explanations

    quantities and metrics related to various topics

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

    Text followed by citations/references

    np_acts-logits-general · gemini-2.0-flash

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -1.68
    <eos>
    -1.41
    ↵↵↵
    -1.32
    ↵
    -1.21
    ↵↵↵↵
    -1.02
    ↵↵↵↵↵
    -1.01
    </h2>
    -0.98
    </h3>
    -0.92
    </tr>
    -0.89
    ↵↵↵↵↵↵↵
    -0.85
    POSITIVE LOGITS
    脚注の使い方
    1.29
     كومونز
    1.25
     للمعارف
    1.10
     autorytatywna
    1.09
    出版年
    1.06
     consultato
    1.03
    WithIOException
    0.98
    GraphicsUnit
    0.97
    లాలు
    0.97
    tvguidetime
    0.95
    Act Density 0.819%

    No Known Activations