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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ffm
    -0.06
     Dare
    -0.06
    _dispatch
    -0.06
     rocking
    -0.06
     sensible
    -0.06
     callBack
    -0.06
    	cv
    -0.06
     Ж
    -0.06
    ,[
    -0.06
    dict
    -0.06
    POSITIVE LOGITS
    (saved
    0.07
    CustomLabel
    0.07
     кла
    0.06
    222
    0.06
     hires
    0.06
    openssl
    0.06
    pt
    0.06
     Xperia
    0.06
    bull
    0.06
    атків
    0.06
    Act Density 0.058%

    No Known Activations