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

    Neuronpedia

    INDEX
    Explanations

    say "the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    recognized
    -0.07
     bureaucracy
    -0.07
    NM
    -0.06
    Jennifer
    -0.06
     ↵↵
    -0.06
    February
    -0.06
     ideologies
    -0.06
     zipper
    -0.06
    Tuesday
    -0.06
    就
    -0.06
    POSITIVE LOGITS
    _ABS
    0.07
     centerpiece
    0.07
     электрон
    0.07
    yasal
    0.06
     vypad
    0.06
    AME
    0.06
     uploader
    0.06
     FileNotFoundException
    0.06
     Üy
    0.06
    .netty
    0.06
    Act Density 0.021%

    No Known Activations