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

    Neuronpedia

    INDEX
    Explanations

    explaining relationships or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lobe
    0.42
     rings
    0.42
     fluttering
    0.41
     disturbance
    0.40
    :
    0.40
     muod
    0.39
     transmettre
    0.38
     rupture
    0.38
    ↵
    0.38
     hänen
    0.38
    POSITIVE LOGITS
    Ard
    0.52
    Comme
    0.49
    Combat
    0.49
    Building
    0.48
    Fc
    0.48
    Payment
    0.47
    Arsenal
    0.47
     Arz
    0.47
    StreetMap
    0.46
    防御
    0.45
    Act Density 0.011%

    No Known Activations