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

    Neuronpedia

    INDEX
    Explanations

    Johnny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	size
    -0.07
    -таки
    -0.07
    渐
    -0.07
    (system
    -0.07
     gardens
    -0.06
     �
    -0.06
    Realm
    -0.06
     month
    -0.06
    /***/
    -0.06
    Tower
    -0.06
    POSITIVE LOGITS
     Mohammad
    0.08
    Johnny
    0.07
     Johnny
    0.07
     Tommy
    0.07
    hey
    0.07
    Jimmy
    0.06
     محمد
    0.06
    셜
    0.06
    Ted
    0.06
     Joey
    0.06
    Act Density 0.046%

    No Known Activations