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

    Neuronpedia

    INDEX
    Explanations

    done

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zich
    -0.06
    }}</
    -0.06
     haired
    -0.06
    boot
    -0.06
     прох
    -0.06
     mej
    -0.06
    ‌ده
    -0.06
     RAD
    -0.06
     recomend
    -0.06
    Times
    -0.06
    POSITIVE LOGITS
     pipeline
    0.07
     drugs
    0.07
     پس
    0.07
    ﾘ
    0.07
    arken
    0.06
     TableName
    0.06
     evt
    0.06
    ('*
    0.06
     समझ
    0.06
    (case
    0.06
    Act Density 0.004%

    No Known Activations