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

    Neuronpedia

    INDEX
    Explanations

    language learning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hostname
    -0.07
    同时
    -0.07
    	onChange
    -0.07
     dirent
    -0.07
    ynchronous
    -0.07
    φό
    -0.06
     IPP
    -0.06
    .every
    -0.06
    omnia
    -0.06
     IMD
    -0.06
    POSITIVE LOGITS
    ....
    0.07
     Camel
    0.06
    ?!↵↵
    0.06
     ロ
    0.06
    -syntax
    0.06
     下跌
    0.06
     […]↵↵
    0.06
    .'↵↵
    0.06
    —↵↵
    0.06
    (jsonObject
    0.06
    Act Density 0.127%

    No Known Activations