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

    Neuronpedia

    INDEX
    Explanations

    Olympics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Geek
    -0.07
    )value
    -0.06
    -0.06
    -phone
    -0.06
     cab
    -0.06
     received
    -0.06
     mouse
    -0.06
    brew
    -0.06
    -0.06
    pel
    -0.06
    POSITIVE LOGITS
    成功
    0.07
    境
    0.06
    anked
    0.06
    !"↵↵
    0.06
     McLaren
    0.06
    \Helpers
    0.06
    0.06
    uggling
    0.06
    _reference
    0.06
     обеспеч
    0.06
    Act Density 0.009%

    No Known Activations