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

    Neuronpedia

    INDEX
    Explanations

    Steam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    attern
    -0.07
    EFAULT
    -0.06
    โ
    -0.06
    سم
    -0.06
    。而
    -0.06
     hled
    -0.06
    lsa
    -0.06
     Coral
    -0.06
     весь
    -0.06
     jedné
    -0.06
    POSITIVE LOGITS
     Steam
    0.09
     quit
    0.08
     autop
    0.07
     ============================================================================↵
    0.06
     Emil
    0.06
    (colors
    0.06
     gallon
    0.06
     hearings
    0.06
     lexical
    0.06
    ,
↵
↵
    0.06
    Act Density 0.002%

    No Known Activations