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

    Neuronpedia

    INDEX
    Explanations

    article

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worst
    -0.07
    aviest
    -0.07
     etkili
    -0.07
    anchors
    -0.07
    वत
    -0.07
     middleware
    -0.07
    Back
    -0.06
     impact
    -0.06
    ิตย
    -0.06
    Channel
    -0.06
    POSITIVE LOGITS
    ・・・↵↵
    0.06
     コ
    0.06
     Saskatchewan
    0.06
     ['$
    0.06
    (Application
    0.06
    ительное
    0.06
     �
    0.06
    Sk
    0.06
    ينة
    0.06
     +↵↵
    0.06
    Act Density 0.038%

    No Known Activations