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

    Neuronpedia

    INDEX
    Explanations

    First

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ház
    0.65
    Shock
    0.64
    िज
    0.64
    shock
    0.62
    cticamente
    0.61
    Place
    0.60
     tasar
    0.60
    इस
    0.59
    endroit
    0.58
    یک
    0.57
    POSITIVE LOGITS
     Yves
    0.70
     kü
    0.66
     droplets
    0.61
     Kue
    0.56
     Ham
    0.55
     intervals
    0.55
    RoundRect
    0.55
     directly
    0.55
     Hutton
    0.55
    ையைக்
    0.55
    Act Density 0.001%

    No Known Activations