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

    Neuronpedia

    INDEX
    Explanations

    age and demographic groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ciaux
    0.75
     descuentos
    0.73
     enfoque
    0.73
     टकराव
    0.72
     револю
    0.72
     দুর্নীতি
    0.72
    糅
    0.72
    itement
    0.71
     अटल
    0.71
     unleashing
    0.70
    POSITIVE LOGITS
     healthy
    2.08
     Healthy
    1.89
    healthy
    1.79
     subjects
    1.78
    Healthy
    1.77
     volunteers
    1.55
    Subjects
    1.52
     males
    1.51
     Subjects
    1.51
    subjects
    1.49
    Act Density 0.270%

    No Known Activations