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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brilliance
    -0.07
     applause
    -0.07
     marvel
    -0.06
     shower
    -0.06
    右手
    -0.06
     lamp
    -0.06
     spur
    -0.06
     popover
    -0.06
     spraw
    -0.06
     wrapped
    -0.06
    POSITIVE LOGITS
    螱
    0.08
    _beg
    0.08
     שאתם
    0.08
    Digite
    0.07
     לעיתים
    0.07
     perverse
    0.07
    ,UnityEngine
    0.07
    䴕
    0.07
    .creation
    0.07
    often
    0.07
    Act Density 0.009%

    No Known Activations