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

    Neuronpedia

    INDEX
    Explanations

    describes actions and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    0.71
    ש
    0.69
    V
    0.68
    K
    0.61
    S
    0.60
    Z
    0.60
    م
    0.59
    Bundes
    0.58
    N
    0.57
    ه
    0.57
    POSITIVE LOGITS
     does
    0.55
     clickView
    0.51
     уче
    0.50
     pago
    0.49
     μα
    0.49
     psychologist
    0.48
     respiratory
    0.48
     Does
    0.47
     Psychologist
    0.46
     театр
    0.45
    Act Density 0.000%

    No Known Activations