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

    Neuronpedia

    INDEX
    Explanations

    lingering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fisheries
    -0.08
    manship
    -0.08
     Reform
    -0.07
    sschutz
    -0.07
    救
    -0.07
    opus
    -0.07
     underwent
    -0.07
     yapmak
    -0.07
    _family
    -0.07
    san
    -0.07
    POSITIVE LOGITS
     lingering
    0.14
     linger
    0.13
     residual
    0.11
     dúvida
    0.10
    久久
    0.09
    Residual
    0.09
     leftover
    0.09
     remnants
    0.09
     باقي
    0.09
     باقی
    0.09
    Act Density 0.012%

    No Known Activations