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

    Neuronpedia

    INDEX
    Explanations

    ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rates
    -0.07
    PosY
    -0.07
     wreckage
    -0.07
    Ї
    -0.07
     endeavors
    -0.07
     deut
    -0.07
     setups
    -0.07
     healer
    -0.07
    \Type
    -0.07
     txn
    -0.07
    POSITIVE LOGITS
    .widget
    0.07
     Sunday
    0.07
     zero
    0.07
    ═
    0.06
     Abdul
    0.06
    .Keyboard
    0.06
    とりあ
    0.06
    al
    0.06
    某个
    0.06
     pol
    0.06
    Act Density 0.001%

    No Known Activations