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

    Neuronpedia

    INDEX
    Explanations

    National Institute acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    psych
    0.87
    FEM
    0.87
    спект
    0.86
     Psycho
    0.86
     Hm
    0.85
    राधना
    0.83
     Jetzt
    0.83
     Espero
    0.82
    irit
    0.82
     Prendre
    0.82
    POSITIVE LOGITS
    ृ
    0.70
    نج
    0.66
    ائمة
    0.63
    ays
    0.62
    iness
    0.61
     মূল
    0.60
     Wals
    0.58
    ordes
    0.58
    case
    0.56
    inol
    0.56
    Act Density 0.001%

    No Known Activations