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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    us
    -0.07
     supervised
    -0.07
    _*
    -0.06
     위치
    -0.06
    Ø
    -0.06
    (features
    -0.06
    店
    -0.06
     llevar
    -0.06
    ы
    -0.06
     GOODS
    -0.06
    POSITIVE LOGITS
    _lng
    0.07
     %%↵
    0.06
     overwhel
    0.06
    	dataType
    0.06
    Ah
    0.05
    dating
    0.05
    Inter
    0.05
    __;↵
    0.05
    だった
    0.05
     GetUser
    0.05
    Act Density 0.009%

    No Known Activations