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
    まだまだ
    -0.08
     بتاريخ
    -0.07
    一双
    -0.07
    Page
    -0.07
    Broker
    -0.06
     persuasion
    -0.06
    xaa
    -0.06
     compare
    -0.06
     Aaron
    -0.06
     govern
    -0.06
    POSITIVE LOGITS
    assertInstanceOf
    0.07
    .strptime
    0.07
    amount
    0.07
    工序
    0.07
    ⇃
    0.06
    מסורת
    0.06
    Ϝ
    0.06
    𬳵
    0.06
    意外
    0.06
    /Register
    0.06
    Act Density 0.200%

    No Known Activations