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

    Neuronpedia

    INDEX
    Explanations

    avoid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    concat
    -0.06
    .Popup
    -0.06
     Πανεπ
    -0.06
     openFileDialog
    -0.06
    _props
    -0.06
     largest
    -0.06
    .len
    -0.06
     incomplete
    -0.06
     Largest
    -0.06
    _letter
    -0.06
    POSITIVE LOGITS
     avoid
    0.15
     avoiding
    0.13
     Avoid
    0.12
     avoided
    0.11
     avoids
    0.10
    Avoid
    0.10
     unavoidable
    0.09
     tránh
    0.09
    avoid
    0.09
     avoidance
    0.09
    Act Density 0.017%

    No Known Activations