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

    Neuronpedia

    INDEX
    Explanations

    lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mož
    -0.07
     rotary
    -0.06
    olut
    -0.06
     Arabian
    -0.06
    .iteritems
    -0.06
     mening
    -0.06
     antique
    -0.06
    奥
    -0.06
     complexities
    -0.06
    世
    -0.06
    POSITIVE LOGITS
    aniem
    0.07
     plusieurs
    0.06
    DED
    0.06
    _selected
    0.06
    _FIND
    0.06
    UINT
    0.06
    ương
    0.06
    ões
    0.06
    اوي
    0.06
    Clients
    0.06
    Act Density 0.124%

    No Known Activations