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

    Neuronpedia

    INDEX
    Explanations

    internet, URLs, dates, Úrsula Iguarán

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.52
    0
    0.49
    2
    0.48
    entry
    0.48
    л
    0.46
     strategic
    0.43
    cc
    0.42
    compet
    0.42
    to
    0.42
    4
    0.42
    POSITIVE LOGITS
     hacerlo
    0.55
     কখনও
    0.54
     être
    0.52
     varie
    0.49
     contraindicated
    0.49
     êtes
    0.48
     există
    0.48
     alcohols
    0.48
     ਹੈ
    0.48
     método
    0.47
    Act Density 0.003%

    No Known Activations