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

    Neuronpedia

    INDEX
    Explanations

    atoms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    διά
    -0.07
     segue
    -0.07
     subst
    -0.07
    _REC
    -0.07
     اجرا
    -0.06
     افزار
    -0.06
     profile
    -0.06
     jsonObject
    -0.06
    _air
    -0.06
     dön
    -0.06
    POSITIVE LOGITS
     />\
    0.06
    겼
    0.06
    έ
    0.06
     hứ
    0.06
     strict
    0.06
    	delay
    0.06
     protections
    0.06
    edelta
    0.06
     Ac
    0.06
    blems
    0.05
    Act Density 0.001%

    No Known Activations