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

    Neuronpedia

    INDEX
    Explanations

    Field

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _De
    -0.07
     �
    -0.07
     tender
    -0.07
    Silver
    -0.06
    ServiceProvider
    -0.06
    _READONLY
    -0.06
    ось
    -0.06
    -era
    -0.06
    로운
    -0.06
    stantial
    -0.06
    POSITIVE LOGITS
     Georges
    0.07
     tận
    0.07
    /files
    0.06
    568
    0.06
     وأن
    0.06
    465
    0.06
    cele
    0.06
    自治
    0.06
     REVIEW
    0.06
    -hole
    0.06
    Act Density 0.000%

    No Known Activations