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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     collaborators
    -0.06
     名無しさん
    -0.06
     Uncle
    -0.06
    _list
    -0.06
    listing
    -0.06
     ハ
    -0.06
    Amazon
    -0.06
     exams
    -0.06
     znam
    -0.06
    ais
    -0.06
    POSITIVE LOGITS
     liberties
    0.07
    _SUR
    0.07
     prejud
    0.06
    =no
    0.06
     ضر
    0.06
    atherine
    0.06
    clide
    0.06
     Carol
    0.06
     खबर
    0.06
     liberty
    0.06
    Act Density 0.068%

    No Known Activations