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

    Neuronpedia

    INDEX
    Explanations

    ide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    subcategory
    -0.07
    גני
    -0.07
    .vehicle
    -0.07
     ]).
    -0.07
    单项
    -0.07
    nemonic
    -0.07
     Особенно
    -0.07
    _category
    -0.07
     Compared
    -0.06
     SetValue
    -0.06
    POSITIVE LOGITS
     ints
    0.07
    iding
    0.06
    ɗ
    0.06
    绮
    0.06
     PASS
    0.06
     désir
    0.06
     Sài
    0.06
     düş
    0.06
     UM
    0.06
    lose
    0.06
    Act Density 0.001%

    No Known Activations