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

    Neuronpedia

    INDEX
    Explanations

    relationships, comparisons, and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opção
    0.79
     garantiert
    0.75
    𝗯
    0.74
     opción
    0.73
     girlfriend
    0.73
     گزینه
    0.73
     overpriced
    0.71
     ficar
    0.70
     permitirá
    0.70
    wife
    0.69
    POSITIVE LOGITS
     phenomena
    0.96
     epistemology
    0.94
     interplay
    0.93
     homeostasis
    0.91
     mechanisms
    0.90
     interactions
    0.90
     processes
    0.89
     phenomenology
    0.88
     sequences
    0.86
     dynamics
    0.85
    Act Density 0.002%

    No Known Activations