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

    Neuronpedia

    INDEX
    Explanations

    Javascript code tests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EL
    -0.07
    �
    -0.06
    	tab
    -0.06
    (course
    -0.06
     emph
    -0.06
     (�
    -0.06
     annonces
    -0.06
    usive
    -0.06
    (always
    -0.06
    oton
    -0.06
    POSITIVE LOGITS
     अच
    0.06
     converting
    0.06
    睡
    0.06
    GameManager
    0.06
     sophisticated
    0.06
     Henry
    0.06
    uplicated
    0.06
    letter
    0.06
    第一次
    0.06
    Definitions
    0.06
    Act Density 0.002%

    No Known Activations