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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fumée
    -0.62
     vägen
    -0.55
     navires
    -0.53
     totiž
    -0.52
     arbete
    -0.52
     stället
    -0.51
    peak
    -0.50
     väg
    -0.48
    post
    -0.48
     semula
    -0.47
    POSITIVE LOGITS
    parsedMessage
    0.84
     contextLoads
    0.78
    WebServlet
    0.59
    AnchorStyles
    0.57
    tonode
    0.57
    NavController
    0.57
    GOTREF
    0.56
    othes
    0.55
     Rud
    0.54
     timers
    0.54
    Act Density 0.001%

    No Known Activations