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

    Neuronpedia

    INDEX
    Explanations

    your response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desirable
    0.95
     encompasses
    0.94
     attrakt
    0.92
     attractive
    0.92
     filed
    0.91
     diskusi
    0.91
     certain
    0.91
     publishes
    0.91
     определенных
    0.90
     exciting
    0.89
    POSITIVE LOGITS
    你有
    1.09
    FixedHeight
    1.09
    Anda
    1.06
     Ejemplo
    1.04
    Selain
    1.01
    你
    0.98
    案例
    0.97
     अभिनंदन
    0.95
    Conse
    0.94
    Equipo
    0.93
    Act Density 0.000%

    No Known Activations