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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ld
    -0.08
    MBER
    -0.07
    Signed
    -0.07
     الفت
    -0.07
     fascination
    -0.07
    essel
    -0.07
     Netz
    -0.07
    _Module
    -0.06
     그냥
    -0.06
    irst
    -0.06
    POSITIVE LOGITS
     even
    0.07
    credits
    0.06
    	sf
    0.06
    _pf
    0.06
     Hera
    0.06
     enriched
    0.06
    潜力
    0.06
     Hit
    0.06
    多项
    0.06
    rag
    0.06
    Act Density 0.045%

    No Known Activations