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

    Neuronpedia

    INDEX
    Explanations

    rotate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istické
    -0.06
     reminiscent
    -0.06
    =torch
    -0.06
    _write
    -0.06
     Colonial
    -0.06
    *pow
    -0.06
    gie
    -0.06
     sed
    -0.06
     genellikle
    -0.06
     shameful
    -0.06
    POSITIVE LOGITS
    .Annotation
    0.08
    ウェ
    0.07
    Scenario
    0.06
     외부
    0.06
    AGED
    0.06
    };↵↵
    0.06
    Discount
    0.06
     مقر
    0.06
    кс
    0.06
     digit
    0.06
    Act Density 0.005%

    No Known Activations