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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旦
    -0.07
     perv
    -0.06
    host
    -0.06
     المر
    -0.06
     �
    -0.06
    	contentPane
    -0.06
    failure
    -0.06
    λεύ
    -0.06
     μεγ
    -0.06
    attached
    -0.06
    POSITIVE LOGITS
     setSearch
    0.06
     Вот
    0.06
    aling
    0.06
    .Hand
    0.06
    iture
    0.06
    .pay
    0.06
    adients
    0.06
    _remain
    0.06
     HIP
    0.06
    als
    0.05
    Act Density 1.539%

    No Known Activations