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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash

    The neuron detects the bracketed flag sequences (e.g. “[L]”, “[R=301,L]”, “[NC]”) used at the end of mod_rewrite rules.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    VD
    -0.06
     جهان
    -0.06
     muht
    -0.06
     Plymouth
    -0.06
     FileInputStream
    -0.06
     Alley
    -0.06
     microsoft
    -0.06
    sy
    -0.06
     Liability
    -0.05
    	not
    -0.05
    POSITIVE LOGITS
    -layer
    0.07
     发
    0.07
     oppress
    0.07
    [],↵
    0.07
     salaries
    0.06
    /edit
    0.06
    RAINT
    0.06
    .song
    0.06
     Rpc
    0.06
    修改
    0.06
    Act Density 0.001%

    No Known Activations