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

    Neuronpedia

    INDEX
    Explanations

    everything or everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্তির
    0.46
     spécifiques
    0.38
    jols
    0.37
     várias
    0.37
     diferentes
    0.36
     змен
    0.36
     interpretación
    0.36
    闱
    0.35
     segí
    0.35
    䐈
    0.35
    POSITIVE LOGITS
     comprehensive
    0.90
     encompass
    0.90
     encompasses
    0.86
     EVERYTHING
    0.86
     encompassing
    0.84
    Comprehensive
    0.83
     Comprehensive
    0.78
     Everywhere
    0.78
    涵盖
    0.76
    Everything
    0.73
    Act Density 0.064%

    No Known Activations