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

    Neuronpedia

    INDEX
    Explanations

    references and citations in the text

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

    references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.51
    Personendaten
    -0.48
    SBATCH
    -0.46
     forState
    -0.42
    Gard
    -0.42
     Stodd
    -0.41
    Tug
    -0.40
    ⓘ
    -0.39
    dyn
    -0.39
    Scen
    -0.38
    POSITIVE LOGITS
     references
    2.19
     References
    1.98
    references
    1.92
    References
    1.90
     REFERENCES
    1.70
    REFERENCES
    1.50
     Referenzen
    1.41
     referencias
    1.40
     références
    1.34
     refs
    1.10
    Act Density 0.014%

    No Known Activations