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

    Neuronpedia

    INDEX
    Explanations

    references to figures or similar items in scientific documents or code

    oai_token-act-pair · gemini-2.0-flash

    figure references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orit
    -0.54
    wal
    -0.54
     OR
    -0.53
    cin
    -0.52
    OR
    -0.50
    atrici
    -0.50
    MR
    -0.50
     Hal
    -0.49
    fo
    -0.48
    ait
    -0.48
    POSITIVE LOGITS
     judiciaire
    0.69
    tvguidetime
    0.68
    trường
    0.66
    __':
    0.66
     tartalomajánló
    0.65
    OGND
    0.64
     feroit
    0.64
    `;
    0.64
     חיצוניים
    0.64
    脚注の使い方
    0.61
    Act Density 2.179%

    No Known Activations