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

    Neuronpedia

    INDEX
    Explanations

    equal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Given
    -0.07
    ancies
    -0.06
    lict
    -0.06
     announcement
    -0.06
     Announcement
    -0.06
     unstoppable
    -0.06
    inctions
    -0.06
    .For
    -0.06
    otton
    -0.06
    anine
    -0.06
    POSITIVE LOGITS
     equal
    0.07
     떨어
    0.07
    iform
    0.07
     slim
    0.07
     рівні
    0.07
    ंब
    0.06
     FactoryGirl
    0.06
     крови
    0.06
    xBA
    0.06
     сум
    0.06
    Act Density 0.008%

    No Known Activations