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

    Neuronpedia

    INDEX
    Explanations

    senses, thoughts, and judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     situaciones
    0.90
    persona
    0.81
    Persona
    0.80
    局面
    0.79
     personas
    0.79
     situações
    0.78
     consultations
    0.78
     mindset
    0.77
    personas
    0.77
     intang
    0.76
    POSITIVE LOGITS
     taste
    0.91
     Taste
    0.87
     Sense
    0.86
     Dante
    0.80
     memory
    0.79
    正確
    0.78
    sense
    0.78
     sense
    0.78
     memória
    0.77
     endurance
    0.76
    Act Density 0.141%

    No Known Activations