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

    Neuronpedia

    INDEX
    Explanations

    emotional and psychological approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    numeric
    0.50
     optimized
    0.50
    optimized
    0.50
     optimizes
    0.49
     Numerical
    0.48
    SYSTEM
    0.48
     alphanumeric
    0.48
     அட்ட
    0.47
     CR
    0.46
     setInterval
    0.46
    POSITIVE LOGITS
     emocional
    0.78
     misog
    0.78
     disrespectful
    0.75
     emotionally
    0.74
     psychologically
    0.73
     emotional
    0.72
     seksual
    0.70
     psychological
    0.70
     romant
    0.70
     भावनात्मक
    0.69
    Act Density 0.156%

    No Known Activations