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

    Neuronpedia

    INDEX
    Explanations

    heavy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     duvar
    -0.07
     getLast
    -0.07
    ply
    -0.06
     tubing
    -0.06
     outspoken
    -0.06
    Div
    -0.06
     selling
    -0.06
    enen
    -0.06
    δει
    -0.06
     complications
    -0.06
    POSITIVE LOGITS
    /is
    0.07
    _OCC
    0.07
     endregion
    0.07
    committee
    0.07
     تلك
    0.07
     окра
    0.06
     проблема
    0.06
    XL
    0.06
    FUNC
    0.06
    FlowLayout
    0.06
    Act Density 0.004%

    No Known Activations