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

    Neuronpedia

    INDEX
    Explanations

    much

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     надо
    -0.06
     relocate
    -0.06
     이는
    -0.06
     توانید
    -0.06
    /rss
    -0.06
     nuevo
    -0.05
     marg
    -0.05
     fringe
    -0.05
     hide
    -0.05
     upside
    -0.05
    POSITIVE LOGITS
    _addresses
    0.08
     Sasha
    0.07
     важ
    0.07
    umes
    0.07
    umbing
    0.07
    permanent
    0.07
    .assertIsNot
    0.07
     Werner
    0.06
    (ord
    0.06
    од
    0.06
    Act Density 0.000%

    No Known Activations