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

    Neuronpedia

    INDEX
    Explanations

    execute

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive—it never fires on any tokens and doesn’t detect any particular pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     MatSnackBar
    -0.06
     repar
    -0.06
    ("[%
    -0.06
    	Port
    -0.06
     왔
    -0.06
    	script
    -0.06
    :error
    -0.06
     شورای
    -0.06
    -budget
    -0.06
    middlewares
    -0.06
    POSITIVE LOGITS
     callable
    0.08
    /E
    0.07
    306
    0.07
    ª
    0.06
    unuz
    0.06
                        
↵
    0.06
    诚
    0.06
    <usize
    0.06
    ursively
    0.06
    oupon
    0.06
    Act Density 0.001%

    No Known Activations