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

    Neuronpedia

    INDEX
    Explanations

    apparent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     étoient
    -0.64
     avoient
    -0.64
     quelcon
    -0.57
     proprement
    -0.56
     ainfi
    -0.56
     étoit
    -0.55
     dépens
    -0.55
     évident
    -0.55
     caballos
    -0.54
    __':
    -0.54
    POSITIVE LOGITS
     force
    0.61
    orsese
    0.57
    StackNavigator
    0.54
     Spirit
    0.53
     expression
    0.51
     propOrder
    0.51
    Initializable
    0.50
     bulk
    0.49
     crack
    0.49
    عا
    0.48
    Act Density 0.028%

    No Known Activations