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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -address
    -0.08
    Pred
    -0.08
    /hash
    -0.08
    אוגוס
    -0.07
    LECTION
    -0.07
     исслед
    -0.07
     Ford
    -0.07
    ald
    -0.07
     guild
    -0.07
    特色
    -0.07
    POSITIVE LOGITS
     chac
    0.07
     Divine
    0.07
    蜀
    0.07
    mai
    0.07
     השי
    0.06
    ??
    0.06
    ={[↵
    0.06
    撑
    0.06
    thé
    0.06
    			 ↵
    0.06
    Act Density 0.050%

    No Known Activations