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

    Neuronpedia

    INDEX
    Explanations

    initial positions and negotiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consp
    0.41
     telemetry
    0.40
     manly
    0.38
    rectomy
    0.38
    beck
    0.38
    verläss
    0.38
     plaie
    0.38
    maschine
    0.38
     Observ
    0.38
    ኸ
    0.38
    POSITIVE LOGITS
     mediation
    0.93
     Dispute
    0.91
     mediator
    0.89
     disputes
    0.88
     conflict
    0.88
     dispute
    0.88
     Conflict
    0.88
     Mediation
    0.85
     negotiation
    0.84
     mediators
    0.84
    Act Density 0.009%

    No Known Activations