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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    红军
    -0.07
    xb
    -0.06
    四处
    -0.06
    mpi
    -0.06
    烩
    -0.06
     rin
    -0.06
    WITH
    -0.06
    冬
    -0.06
     ambit
    -0.06
    _Free
    -0.06
    POSITIVE LOGITS
     sequentially
    0.07
     précéd
    0.07
    pseudo
    0.07
    formulario
    0.07
    请注意
    0.07
    /contentassist
    0.07
    /dialog
    0.07
     louder
    0.07
     получ
    0.07
    professional
    0.07
    Act Density 0.003%

    No Known Activations