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

    Neuronpedia

    INDEX
    Explanations

    sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    					↵
    -0.08
    		↵
    -0.07
     Kinder
    -0.06
    ็ม
    -0.06
     провед
    -0.06
     withstand
    -0.06
     Clark
    -0.06
    Clark
    -0.06
     말이
    -0.06
     يجب
    -0.06
    POSITIVE LOGITS
     Yemen
    0.06
    HTTPRequestOperation
    0.06
    าภ
    0.06
    _PRI
    0.06
    _unregister
    0.06
    IfNeeded
    0.06
    91
    0.06
     thiện
    0.06
     ENTER
    0.06
    γω
    0.06
    Act Density 0.005%

    No Known Activations