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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Бог
    -0.07
     letzten
    -0.06
    ENSOR
    -0.06
     desired
    -0.06
    irie
    -0.06
    agy
    -0.06
    �
    -0.06
    291
    -0.06
    EDIT
    -0.06
    ISON
    -0.06
    POSITIVE LOGITS
     ports
    0.08
     catastrophic
    0.07
     Yorkers
    0.07
     Warfare
    0.07
     pnl
    0.07
     Rencontres
    0.07
     carniv
    0.07
    .Complete
    0.06
    asename
    0.06
     unleash
    0.06
    Act Density 0.006%

    No Known Activations