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

    Neuronpedia

    INDEX
    Explanations

    negotiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    懲
    0.81
    ꞌ
    0.77
     pà
    0.75
     Bitter
    0.73
    四十
    0.71
     bitter
    0.70
     مە
    0.70
     미
    0.69
     Михаил
    0.69
    宓
    0.67
    POSITIVE LOGITS
     Negotiation
    0.73
     Sy
    0.73
    <0xB5>
    0.71
     historias
    0.70
    sy
    0.70
     negotiation
    0.69
     الرغم
    0.69
     negotiators
    0.69
     খুলে
    0.68
     negotiated
    0.68
    Act Density 0.007%

    No Known Activations