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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сент
    -0.07
    :::|
    -0.07
    (crate
    -0.07
     Quốc
    -0.06
     Ones
    -0.06
     السكان
    -0.06
    혼
    -0.06
    лі
    -0.06
     aust
    -0.06
    ู
    -0.06
    POSITIVE LOGITS
    _softmax
    0.06
     produce
    0.06
    ny
    0.06
    	ERR
    0.06
     softmax
    0.06
    EventHandler
    0.06
    okino
    0.06
    (itemId
    0.06
    aydı
    0.06
    etri
    0.05
    Act Density 0.000%

    No Known Activations