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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Glad
    -0.07
     depicts
    -0.07
     Recreation
    -0.06
     Republic
    -0.06
     dy
    -0.06
     your
    -0.06
     Severity
    -0.06
    Knowing
    -0.06
    urgeon
    -0.06
     Your
    -0.06
    POSITIVE LOGITS
    /apimachinery
    0.07
    ิธ
    0.07
    keiten
    0.07
     сух
    0.07
     حل
    0.06
     государ
    0.06
     filling
    0.06
    (cb
    0.06
     قي
    0.06
    ором
    0.06
    Act Density 0.016%

    No Known Activations