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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dto
    -0.06
    *)(
    -0.06
     Barbara
    -0.06
    Focus
    -0.06
    _s
    -0.06
     Philipp
    -0.06
     Staten
    -0.05
    958
    -0.05
    (len
    -0.05
    enge
    -0.05
    POSITIVE LOGITS
    ヾ
    0.07
     ヾ
    0.07
    �i
    0.07
    ología
    0.07
    بط
    0.07
     |:
    0.07
    jp
    0.07
    .playlist
    0.06
    .det
    0.06
     pobl
    0.06
    Act Density 0.000%

    No Known Activations