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

    Neuronpedia

    INDEX
    Explanations

    agenda, draining

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ците
    0.65
    <0x9D>
    0.61
     লাগে
    0.60
     ব্যবসায়
    0.59
    ството
    0.58
     끼
    0.57
    출
    0.57
    :',
    0.57
    ओसी
    0.56
    entu
    0.56
    POSITIVE LOGITS
    agenda
    0.73
    Drain
    0.66
     wake
    0.65
    drain
    0.63
     mauris
    0.63
    枯
    0.62
    Agenda
    0.62
    bang
    0.62
     renegoti
    0.62
     draining
    0.62
    Act Density 0.004%

    No Known Activations