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

    Neuronpedia

    INDEX
    Explanations

    code with coordinates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BCE
    -0.07
    ‐'
    -0.07
    _CALC
    -0.06
     introductory
    -0.06
    یم
    -0.06
     Territory
    -0.06
    imax
    -0.06
     |_
    -0.06
    ůst
    -0.06
     само
    -0.06
    POSITIVE LOGITS
    ssl
    0.06
    こちら
    0.06
    ्छ
    0.06
    ственного
    0.06
    dives
    0.06
    되고
    0.06
     sparks
    0.06
    女子
    0.06
    assertSame
    0.06
     Seeking
    0.06
    Act Density 0.036%

    No Known Activations