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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    masters
    -0.08
     hind
    -0.07
    ANDROID
    -0.07
    warning
    -0.07
     xin
    -0.07
    _quest
    -0.07
     quir
    -0.07
    با
    -0.07
    Healthy
    -0.07
    Ø
    -0.06
    POSITIVE LOGITS
    	startActivity
    0.06
     �
    0.06
    myfile
    0.06
    ()
↵
↵
↵
    0.06
    __)↵↵↵
    0.06
     Dedicated
    0.06
     atoi
    0.06
        
↵    
↵
    0.06
     simples
    0.06
    ？”↵↵
    0.06
    Act Density 0.008%

    No Known Activations