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

    Neuronpedia

    INDEX
    Explanations

    instead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Europe
    -0.07
     رب
    -0.07
     buffered
    -0.07
     oft
    -0.07
    phi
    -0.06
    599
    -0.06
    443
    -0.06
     DMA
    -0.06
     rychle
    -0.06
     recorded
    -0.06
    POSITIVE LOGITS
     instead
    0.13
    instead
    0.10
     Instead
    0.09
    Instead
    0.09
     Instituto
    0.08
     stabbed
    0.07
    .START
    0.07
    (inplace
    0.07
    ;)
    0.07
    last
    0.07
    Act Density 0.017%

    No Known Activations