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

    Neuronpedia

    INDEX
    Explanations

    OK?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     décl
    0.55
     confident
    0.55
     breathed
    0.54
     perished
    0.54
    ²,
    0.52
     withered
    0.52
     maintenir
    0.51
     .,
    0.50
     irresist
    0.50
     defensor
    0.49
    POSITIVE LOGITS
    on
    0.54
    स
    0.52
    manifolds
    0.50
    leap
    0.50
    enial
    0.50
    方案
    0.49
    럽
    0.49
    环节
    0.49
    airplane
    0.48
     समूहों
    0.48
    Act Density 0.000%

    No Known Activations