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

    Neuronpedia

    INDEX
    Explanations

    shock or surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pag
    -0.07
     humidity
    -0.07
    ved
    -0.06
     Θεσσα
    -0.06
    _lstm
    -0.06
     createStackNavigator
    -0.06
     oppressed
    -0.06
    _kwargs
    -0.06
     hrs
    -0.06
    (serializer
    -0.06
    POSITIVE LOGITS
     shocking
    0.08
     shocked
    0.08
     stunned
    0.08
     놀
    0.07
    ází
    0.06
     surprise
    0.06
    rubu
    0.06
    quisition
    0.06
     GAL
    0.06
    .when
    0.06
    Act Density 0.062%

    No Known Activations