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
     Mits
    -0.07
    (observer
    -0.06
    _hs
    -0.06
     Hao
    -0.06
    @js
    -0.06
     Payments
    -0.06
    571
    -0.06
    _buckets
    -0.06
     зай
    -0.06
     Sarah
    -0.06
    POSITIVE LOGITS
    ComputedStyle
    0.07
     skiing
    0.06
     fate
    0.06
     sew
    0.06
     Examiner
    0.06
    :set
    0.06
     disappeared
    0.06
     VER
    0.06
     appearance
    0.06
    ografie
    0.06
    Act Density 0.000%

    No Known Activations