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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uc
    -0.07
     CMS
    -0.07
    ,’”
    -0.07
    ाव
    -0.06
    >'+
    -0.06
    CCCC
    -0.06
     wäre
    -0.06
     Felipe
    -0.06
     logout
    -0.06
     entender
    -0.06
    POSITIVE LOGITS
     humanity
    0.06
    のだろう
    0.06
    _PKG
    0.06
    лаш
    0.06
    skill
    0.06
    physical
    0.06
     Sonata
    0.06
    -hard
    0.05
    Trying
    0.05
     показ
    0.05
    Act Density 0.010%

    No Known Activations