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

    Neuronpedia

    INDEX
    Explanations

    String manipulation and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    谢谢你
    -0.07
    努力
    -0.06
    Those
    -0.06
    השקעה
    -0.06
    失落
    -0.06
    Spacer
    -0.06
     Nẵ
    -0.06
    🐫
    -0.06
    autorelease
    -0.06
     SUMMARY
    -0.06
    POSITIVE LOGITS
    하여
    0.07
     Pall
    0.07
    干线
    0.07
    rés
    0.07
     chrom
    0.07
    ayment
    0.07
     triplet
    0.07
     pleasant
    0.07
     בעל
    0.07
    经商
    0.07
    Act Density 0.006%

    No Known Activations