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

    Neuronpedia

    INDEX
    Explanations

    brought together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bravery
    1.12
     marvelous
    1.09
    他
    1.09
     smiling
    1.09
     он
    1.09
     wonderful
    1.08
     magnific
    1.06
     YOU
    1.06
    他不
    1.05
     jov
    1.05
    POSITIVE LOGITS
     ổ
    1.12
     quốc
    1.07
     hãng
    1.07
    ńst
    1.06
     종합
    1.06
     정부
    1.06
    boolean
    1.03
     cặp
    1.03
    setdefault
    1.02
    governmental
    1.01
    Act Density 0.111%

    No Known Activations