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

    Neuronpedia

    INDEX
    Explanations

    code/data tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }`}↵
    -0.07
    FAILURE
    -0.07
     #↵
    -0.07
    /****************************************************************
    -0.06
     readline
    -0.06
    CVE
    -0.06
    URN
    -0.06
     зуст
    -0.06
    __))↵
    -0.06
    ione
    -0.06
    POSITIVE LOGITS
    /as
    0.07
     looks
    0.06
    ونية
    0.06
     repository
    0.06
     nucle
    0.06
     contempt
    0.06
    _floor
    0.06
    =create
    0.06
    하
    0.06
    -container
    0.06
    Act Density 0.017%

    No Known Activations