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

    Neuronpedia

    INDEX
    Explanations

    researchers and their actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.72
     brunâtre
    0.66
     antich
    0.66
     iP
    0.65
     postérieures
    0.63
     shutterstock
    0.63
     hémorro
    0.62
     ayatan
    0.61
     newborns
    0.60
    ยาน
    0.59
    POSITIVE LOGITS
    ag
    0.79
    z
    0.69
    م
    0.68
    ม
    0.66
    v
    0.63
    а
    0.63
    x
    0.59
    ed
    0.58
    ad
    0.58
    y
    0.57
    Act Density 0.035%

    No Known Activations