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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MSG
    -0.08
     вод
    -0.07
     لدي
    -0.06
     Duch
    -0.06
    _HEAD
    -0.06
     Skype
    -0.06
     Gap
    -0.06
     piles
    -0.06
     Semester
    -0.06
     Seasons
    -0.06
    POSITIVE LOGITS
     Pike
    0.07
    alarından
    0.07
    工具
    0.06
     InvalidOperationException
    0.06
     residents
    0.06
    notation
    0.06
     Conservatives
    0.06
     *)
    0.06
    _elems
    0.06
     replies
    0.06
    Act Density 0.004%

    No Known Activations