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

    Neuronpedia

    INDEX
    Explanations

    Academic discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teor
    -0.07
     jin
    -0.07
    ربع
    -0.06
    oque
    -0.06
    577
    -0.06
    .check
    -0.06
    .selected
    -0.06
    /mod
    -0.06
    USER
    -0.06
    Brit
    -0.06
    POSITIVE LOGITS
    基于
    0.07
    発売
    0.07
    сутств
    0.07
    ／／
    0.07
     assumed
    0.06
    _REGION
    0.06
     sharedApplication
    0.06
     DESCRIPTION
    0.06
     placer
    0.06
    getClient
    0.06
    Act Density 0.078%

    No Known Activations