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

    Neuronpedia

    INDEX
    Explanations

    reflective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utut
    -0.07
    \system
    -0.07
    _skills
    -0.07
    .return
    -0.06
    	class
    -0.06
    Us
    -0.06
    ріб
    -0.06
     kayıt
    -0.06
    
    -0.06
    anford
    -0.06
    POSITIVE LOGITS
     �
    0.07
     <<
    0.06
     â
    0.06
    ONDON
    0.06
    /native
    0.06
     erb
    0.06
     ανά
    0.06
     Edited
    0.06
     Mal
    0.06
    >↵
    0.06
    Act Density 0.000%

    No Known Activations