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

    Neuronpedia

    INDEX
    Explanations

    say "b" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وده
    -0.07
     Gordon
    -0.06
    芝
    -0.06
    -hearted
    -0.06
    350
    -0.06
    088
    -0.06
    �
    -0.06
    Opening
    -0.06
    我们
    -0.06
    Okay
    -0.06
    POSITIVE LOGITS
    	virtual
    0.07
    onu
    0.06
     thư
    0.06
    	rs
    0.06
    .Id
    0.06
    _player
    0.06
     signIn
    0.06
     تع
    0.06
    <small
    0.06
     cautioned
    0.06
    Act Density 0.103%

    No Known Activations