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

    Neuronpedia

    INDEX
    Explanations

    Number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SmartPointer
    -0.07
     Side
    -0.07
    Boxes
    -0.07
     Score
    -0.07
     част
    -0.07
     Scenario
    -0.07
    valid
    -0.07
     chocolate
    -0.06
     side
    -0.06
    行政
    -0.06
    POSITIVE LOGITS
    _rr
    0.07
    μβρίου
    0.06
    (ls
    0.06
    ")!=
    0.06
    binding
    0.06
    .mixer
    0.06
    xon
    0.06
    (lst
    0.06
     distinctly
    0.06
     ls
    0.06
    Act Density 0.009%

    No Known Activations