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

    Neuronpedia

    INDEX
    Explanations

    Twitter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     watched
    -0.06
    Nil
    -0.06
     malloc
    -0.06
    गढ
    -0.06
    기로
    -0.06
     Readonly
    -0.06
    	char
    -0.06
    ому
    -0.06
    _ptrs
    -0.06
    =model
    -0.06
    POSITIVE LOGITS
    )‏
    0.07
    WT
    0.07
     subsidiaries
    0.07
     disclosing
    0.07
    ieder
    0.07
     Twitter
    0.07
     tweeted
    0.07
    (rr
    0.07
     tweeting
    0.06
    یز
    0.06
    Act Density 0.006%

    No Known Activations