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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (exit
    -0.08
    -debug
    -0.08
    -can
    -0.08
     aitab
    -0.08
     বিদ
    -0.08
    unlink
    -0.07
     eksister
    -0.07
     жив
    -0.07
     unlink
    -0.07
    -existing
    -0.07
    POSITIVE LOGITS
     imperial
    0.08
     calculators
    0.08
     Power
    0.08
     szko
    0.07
     Euler
    0.07
     ECG
    0.07
     textbooks
    0.07
     assumption
    0.07
     textbook
    0.07
     cartes
    0.07
    Act Density 0.091%

    No Known Activations