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

    Neuronpedia

    INDEX
    Explanations

    opening brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abolition
    -0.06
    ænd
    -0.06
    床
    -0.06
    _fin
    -0.06
     آرام
    -0.06
    frames
    -0.06
    (href
    -0.06
     Diaz
    -0.06
    viar
    -0.06
     黄
    -0.06
    POSITIVE LOGITS
     -$
    0.07
    OLLOW
    0.07
    _AB
    0.06
    /↵↵↵↵
    0.06
    े�
    0.06
    usize
    0.06
     mocking
    0.06
    771
    0.06
     unpl
    0.06
    assertSame
    0.06
    Act Density 0.033%

    No Known Activations