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

    Neuronpedia

    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attribution
    -0.06
    연구
    -0.06
     лист
    -0.06
    Probably
    -0.06
     jade
    -0.06
    ausible
    -0.06
     warns
    -0.06
    .tags
    -0.06
    fu
    -0.06
    uml
    -0.06
    POSITIVE LOGITS
     Czech
    0.07
     langue
    0.07
     rhet
    0.06
    .FlatAppearance
    0.06
    _prim
    0.06
    -Class
    0.06
     loa
    0.06
    维
    0.06
     الدر
    0.06
     �
    0.06
    Act Density 0.029%

    No Known Activations