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

    Neuronpedia

    INDEX
    Explanations

    draft and trade signings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abschnitt
    0.48
     discoloration
    0.40
     출력
    0.40
     Thoreau
    0.39
     semicol
    0.39
     Anwendung
    0.39
     primitive
    0.39
     کودکان
    0.38
     Побе
    0.38
     spontaneously
    0.38
    POSITIVE LOGITS
     signings
    1.04
     signing
    0.85
    draft
    0.85
     draft
    0.83
     drafting
    0.82
     trades
    0.81
    Draft
    0.79
     negotiations
    0.77
     drafted
    0.77
     negotiating
    0.76
    Act Density 0.006%

    No Known Activations