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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rankings
    -0.07
     같
    -0.07
     EB
    -0.07
    .iter
    -0.07
    (conf
    -0.07
    -Mar
    -0.06
    wm
    -0.06
    _Min
    -0.06
    .MouseEvent
    -0.06
    (employee
    -0.06
    POSITIVE LOGITS
     Birleşik
    0.06
     أعلام
    0.06
    ppelin
    0.06
    cls
    0.06
    	Common
    0.06
     flats
    0.06
     servic
    0.06
     Jazeera
    0.06
    ;base
    0.06
     Fuji
    0.06
    Act Density 0.035%

    No Known Activations