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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    שחקן
    -0.07
    睢
    -0.07
    🥺
    -0.07
    🗽
    -0.07
     Craigslist
    -0.07
     sharedPreferences
    -0.07
     createStackNavigator
    -0.07
     thriller
    -0.07
    ༜
    -0.07
     therefore
    -0.07
    POSITIVE LOGITS
     castle
    0.07
    elivery
    0.07
    _tt
    0.07
    adoop
    0.07
    _var
    0.07
    astr
    0.07
     narrower
    0.07
     �
    0.07
     Kernel
    0.06
    _pages
    0.06
    Act Density 0.001%

    No Known Activations