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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amendment
    -0.07
     DMA
    -0.07
    bial
    -0.07
     ability
    -0.07
    Building
    -0.06
    _LINES
    -0.06
     Commonwealth
    -0.06
     コ
    -0.06
     hall
    -0.06
     Shepard
    -0.06
    POSITIVE LOGITS
    odon
    0.06
    (SS
    0.06
    DIFF
    0.06
     exemplo
    0.06
    Exporter
    0.06
    ected
    0.06
    евой
    0.06
    aser
    0.06
     также
    0.06
    arer
    0.06
    Act Density 0.036%

    No Known Activations