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

    Neuronpedia

    INDEX
    Explanations

    high-frequency functional or organizational terms and references

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

    references and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Biôgrafia
    -0.52
    iest
    -0.52
    quire
    -0.50
    eably
    -0.50
    iada
    -0.49
    assis
    -0.49
    hisattva
    -0.48
    este
    -0.48
    esthetics
    -0.48
    ology
    -0.47
    POSITIVE LOGITS
    <bos>
    0.47
    Personendaten
    0.44
    endregion
    0.44
    +#+
    0.44
    Cyfeiriadau
    0.40
    IContainer
    0.39
     Recursos
    0.38
     lecteurs
    0.38
     debole
    0.37
    endsection
    0.36
    Act Density 0.000%

    No Known Activations