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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivering
    -0.07
    icho
    -0.07
    _dual
    -0.07
    _sold
    -0.06
     journals
    -0.06
     dwell
    -0.06
    istrat
    -0.06
     *>(
    -0.06
     yelling
    -0.06
     chooser
    -0.06
    POSITIVE LOGITS
     попыт
    0.06
    пор
    0.06
     Bayesian
    0.06
     è
    0.06
    "\↵
    0.06
     Bayern
    0.06
     jogo
    0.06
     سپ
    0.06
    mani
    0.06
    τοι
    0.06
    Act Density 0.000%

    No Known Activations