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

    Neuronpedia

    INDEX
    Explanations

    From plus context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stabilizes
    0.44
     prohibits
    0.43
     అధికారులు
    0.42
     collaborated
    0.42
     coloque
    0.39
     acknowledges
    0.39
    backed
    0.39
     держать
    0.39
     Fahrzeuge
    0.39
     melibatkan
    0.38
    POSITIVE LOGITS
     whence
    0.95
     standpoint
    0.93
     thence
    0.85
     ومن
    0.76
     From
    0.75
    с
    0.73
    From
    0.70
    ومن
    0.68
     afar
    0.67
    from
    0.66
    Act Density 0.021%

    No Known Activations