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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mur
    -0.07
    知道
    -0.07
    ())))
    -0.07
    해서
    -0.06
    }catch
    -0.06
     onions
    -0.06
    _fixed
    -0.06
     ################################################################
    -0.06
    Stores
    -0.06
     Polo
    -0.06
    POSITIVE LOGITS
    ительность
    0.06
    	th
    0.06
    uela
    0.06
    .Enqueue
    0.06
     示
    0.06
     cellForRowAt
    0.06
     ion
    0.06
    -before
    0.06
    	tests
    0.05
    felt
    0.05
    Act Density 0.022%

    No Known Activations