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

    Neuronpedia

    INDEX
    Explanations

    debugging code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Time
    -0.09
     culmin
    -0.08
     Magn
    -0.08
     Leh
    -0.08
     evid
    -0.08
     scarcely
    -0.08
     رود
    -0.08
    OLF
    -0.08
    EOS
    -0.07
     insinu
    -0.07
    POSITIVE LOGITS
     workaround
    0.12
     redesign
    0.11
     либо
    0.10
     entweder
    0.10
     either
    0.10
     redef
    0.10
     remedies
    0.10
     remedy
    0.09
     remed
    0.09
     устран
    0.09
    Act Density 0.045%

    No Known Activations