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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =r
    -0.06
     tg
    -0.06
     '{}'
    -0.06
    _alarm
    -0.06
    Transparent
    -0.06
    SmartyHeaderCode
    -0.05
     ans
    -0.05
    ={"
    -0.05
    password
    -0.05
     γ
    -0.05
    POSITIVE LOGITS
     международ
    0.07
     señ
    0.06
     unbiased
    0.06
    .Listener
    0.06
     دید
    0.06
     편
    0.06
    uji
    0.06
     Tit
    0.06
    	
↵
↵
    0.06
     Tested
    0.06
    Act Density 0.005%

    No Known Activations