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

    Neuronpedia

    INDEX
    Explanations

    formatting code

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of string‐formatting calls (i.e. the “format” method or function being invoked).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _posts
    -0.08
     Boyle
    -0.07
    _sphere
    -0.07
     Mighty
    -0.07
     Ridley
    -0.07
    	let
    -0.07
     dysfunction
    -0.06
     walnut
    -0.06
     commented
    -0.06
    \Product
    -0.06
    POSITIVE LOGITS
     Amit
    0.06
    ------↵↵
    0.06
     Contributor
    0.06
     ノ
    0.05
    adr
    0.05
    advertisement
    0.05
     fors
    0.05
     turquoise
    0.05
    };
↵
    0.05
     librarian
    0.05
    Act Density 0.008%

    No Known Activations