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

    Neuronpedia

    INDEX
    Explanations

    security guarantees and agreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Psic
    0.46
    纷
    0.46
    泽
    0.46
     stratégie
    0.45
     Strategy
    0.44
     aprovechar
    0.43
     мани
    0.42
    یو
    0.42
     Disponible
    0.42
     беремен
    0.42
    POSITIVE LOGITS
     guarantees
    0.58
     guarantee
    0.57
     concessions
    0.57
     agreed
    0.55
    agree
    0.51
    INSTALL
    0.50
    commit
    0.47
     concession
    0.47
     vissa
    0.46
    allow
    0.46
    Act Density 0.032%

    No Known Activations