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

    Neuronpedia

    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wallace
    -0.08
     mush
    -0.07
     Lorem
    -0.07
    ؈
    -0.07
    庹
    -0.07
    rawer
    -0.07
     numOf
    -0.07
     Fon
    -0.06
     VX
    -0.06
    自分の
    -0.06
    POSITIVE LOGITS
    stroke
    0.07
    Bad
    0.07
    浅
    0.07
     scholar
    0.07
    =https
    0.07
     stained
    0.06
    Investigators
    0.06
    خيص
    0.06
     또한
    0.06
    -----------↵
    0.06
    Act Density 0.001%

    No Known Activations