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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAX
    -0.06
    Tim
    -0.06
     lament
    -0.06
     χώ
    -0.06
     Toledo
    -0.06
    =[↵
    -0.06
    句
    -0.06
    ndx
    -0.06
     Spin
    -0.06
    าผ
    -0.06
    POSITIVE LOGITS
    ilogue
    0.07
    arious
    0.07
     політики
    0.06
    SearchParams
    0.06
     routine
    0.06
    ぇ
    0.06
    (layer
    0.06
    	DB
    0.06
     waitFor
    0.06
    (isinstance
    0.06
    Act Density 0.065%

    No Known Activations