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

    Neuronpedia

    INDEX
    Explanations

    online arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Silver
    -0.08
     Knife
    -0.07
     Function
    -0.07
    段
    -0.06
    ีน
    -0.06
    -0.06
    анный
    -0.06
    orious
    -0.06
     Garland
    -0.06
    314
    -0.06
    POSITIVE LOGITS
     hunger
    0.07
    Jul
    0.07
     relies
    0.06
    .loadData
    0.06
     Vũ
    0.06
    Similarly
    0.06
    PARATOR
    0.06
     Rupert
    0.06
    ؛
    0.06
    _audit
    0.06
    Act Density 0.072%

    No Known Activations