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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SW
    -0.06
     prot
    -0.06
     �
    -0.06
    ần
    -0.06
    茨
    -0.06
     เก
    -0.06
     ucwords
    -0.06
    ift
    -0.06
    osals
    -0.06
    	tx
    -0.05
    POSITIVE LOGITS
    Regression
    0.07
     nồi
    0.07
     إليه
    0.07
    ?’
    0.07
    看看
    0.07
    reira
    0.07
    未
    0.06
    “↵↵
    0.06
    一次
    0.06
    皆
    0.06
    Act Density 0.045%

    No Known Activations