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

    Neuronpedia

    INDEX
    Explanations

    Code with "i" variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Apollo
    -0.08
    Transportation
    -0.08
    cribes
    -0.08
     verfol
    -0.08
    Pays
    -0.08
     fragmented
    -0.08
    08
    -0.08
    fragment
    -0.08
    rafts
    -0.08
    အသ
    -0.08
    POSITIVE LOGITS
     collapsing
    0.08
     ITER
    0.07
    ITER
    0.07
    =i
    0.07
    trial
    0.07
     linen
    0.07
     giả
    0.07
    试
    0.07
     int
    0.07
     Iter
    0.07
    Act Density 0.004%

    No Known Activations