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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、何
    -0.07
     chants
    -0.06
    过去
    -0.06
     bats
    -0.06
    털
    -0.06
    ¥
    -0.06
     Ψ
    -0.06
    сит
    -0.06
    PK
    -0.06
    医
    -0.06
    POSITIVE LOGITS
    spir
    0.07
    limit
    0.07
    _eval
    0.07
    Reflect
    0.06
    acb
    0.06
    _Header
    0.06
     результ
    0.06
     wiring
    0.06
     française
    0.06
    raises
    0.06
    Act Density 0.063%

    No Known Activations