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

    Neuronpedia

    INDEX
    Explanations

    configuration settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sembling
    0.58
    মন্ত্রী
    0.53
     CreateWindow
    0.53
    g
    0.52
    r
    0.51
    d
    0.50
    ر
    0.49
    EndTime
    0.49
    anting
    0.48
    雦
    0.48
    POSITIVE LOGITS
     adiab
    0.52
     fuerza
    0.51
     conex
    0.51
     trocar
    0.51
     deck
    0.50
     meilleur
    0.49
     splice
    0.47
     Detalles
    0.47
     descent
    0.47
     patient
    0.46
    Act Density 0.000%

    No Known Activations