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

    Neuronpedia

    INDEX
    Explanations

    impact, influence, power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Detection
    0.99
     보안
    0.89
     detección
    0.83
     Geschäft
    0.82
    Detection
    0.81
     Clínica
    0.80
     Detecting
    0.80
     görev
    0.80
     melawan
    0.80
    Optimal
    0.80
    POSITIVE LOGITS
     celebrities
    1.01
    consumers
    0.94
    platforms
    0.91
    polls
    0.90
     platforms
    0.90
    displays
    0.88
    куру
    0.88
    cultures
    0.88
    platform
    0.87
    efois
    0.87
    Act Density 0.050%

    No Known Activations