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

    Neuronpedia

    INDEX
    Explanations

    Article or entry beginnings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     மாத
    -0.09
    Ber
    -0.09
     tableau
    -0.09
     tableaux
    -0.08
     chu
    -0.08
     shu
    -0.08
    oleon
    -0.08
     Ches
    -0.07
     byo
    -0.07
     ')'
    -0.07
    POSITIVE LOGITS
     ختم
    0.07
    FUNCTION
    0.07
     mortgages
    0.07
     condemn
    0.07
     wallets
    0.07
    (employee
    0.07
     Walking
    0.07
    LOG
    0.07
     muhiim
    0.07
     CAPITAL
    0.07
    Act Density 0.024%

    No Known Activations