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

    Neuronpedia

    INDEX
    Explanations

    finite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (z
    -0.06
     Link
    -0.06
     darker
    -0.06
    (X
    -0.06
     blind
    -0.06
     Cards
    -0.06
     بازیگر
    -0.06
     standout
    -0.06
     Lup
    -0.06
     XR
    -0.06
    POSITIVE LOGITS
     finite
    0.11
     Finite
    0.09
    met
    0.08
     Zeit
    0.08
    et
    0.07
     Randy
    0.07
    eti
    0.07
    FIN
    0.07
    ennie
    0.07
    uti
    0.07
    Act Density 0.004%

    No Known Activations