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

    Neuronpedia

    INDEX
    Explanations

    exponent simplification problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Predict
    -0.06
     Jahre
    -0.06
    Batman
    -0.06
     vertically
    -0.06
    _SINGLE
    -0.06
    _outputs
    -0.05
    North
    -0.05
     invasion
    -0.05
     ApplicationRecord
    -0.05
    steps
    -0.05
    POSITIVE LOGITS
     -->
↵
↵
    0.07
    nob
    0.07
    <Link
    0.06
    urchase
    0.06
    oins
    0.06
    meal
    0.06
    enus
    0.06
     gig
    0.06
    管理
    0.06
    (ID
    0.06
    Act Density 0.004%

    No Known Activations