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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to project requirements and documentation

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

    foreign and programming words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    -0.54
    a
    -0.52
    o
    -0.48
    ه
    -0.47
    ceae
    -0.47
    ा
    -0.46
     []:
    -0.46
    theria
    -0.46
    ا
    -0.44
     Fra
    -0.43
    POSITIVE LOGITS
     itſelf
    0.72
    SBATCH
    0.71
     himſelf
    0.68
    featureID
    0.67
     leſs
    0.63
     himself
    0.58
    帖最后由
    0.58
    HasForeignKey
    0.57
     perſon
    0.54
    นะครับ
    0.54
    Act Density 0.015%

    No Known Activations