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

    Neuronpedia

    INDEX
    Explanations

    Cannot access external content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Something
    -0.09
     trzeba
    -0.08
     Anderson
    -0.08
     Inspired
    -0.08
     eventueel
    -0.08
     mgr
    -0.08
     Helf
    -0.08
    él
    -0.08
     weinig
    -0.08
    Lu
    -0.08
    POSITIVE LOGITS
     accurately
    0.10
     unless
    0.10
    unless
    0.09
    _exact
    0.09
     ούτε
    0.09
    nor
    0.09
     سوى
    0.09
     apologies
    0.09
     עב
    0.08
     nor
    0.08
    Act Density 0.020%

    No Known Activations