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

    Neuronpedia

    INDEX
    Explanations

    barely audible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DCs
    0.66
     invariant
    0.64
     trăm
    0.64
     monotonically
    0.63
    כות
    0.60
     pith
    0.60
    preferably
    0.60
    DummyView
    0.60
     indetermin
    0.59
    TARIFF
    0.59
    POSITIVE LOGITS
    haft
    0.60
    ot
    0.59
     भेट
    0.57
     लढ
    0.55
     réparation
    0.55
    ामुळे
    0.54
     accident
    0.53
    くらい
    0.52
    认证
    0.51
    িয়াল
    0.51
    Act Density 0.005%

    No Known Activations