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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
    turned
    -0.06
    chten
    -0.06
     hled
    -0.06
    ozilla
    -0.06
    ailand
    -0.06
     remotely
    -0.06
     tủ
    -0.06
    oya
    -0.06
    敦
    -0.06
    POSITIVE LOGITS
    stateProvider
    0.07
    Questions
    0.07
    <ID
    0.07
     comply
    0.07
     今
    0.06
     persec
    0.06
    �
    0.06
    	db
    0.06
    /in
    0.06
     список
    0.06
    Act Density 0.002%

    No Known Activations