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

    Neuronpedia

    INDEX
    Explanations

    project trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     déput
    0.39
     applicationId
    0.38
     assigns
    0.38
     কিছুই
    0.38
     کرسکتے
    0.38
     hudson
    0.38
     indexOf
    0.37
     catalyze
    0.37
     authorize
    0.36
     Iterate
    0.36
    POSITIVE LOGITS
    SY
    0.42
    ન્મ
    0.41
    毅
    0.41
    Jade
    0.38
     असामान्य
    0.38
    যু
    0.38
    ရင်
    0.38
    νε
    0.37
     barren
    0.37
     ორი
    0.37
    Act Density 0.000%

    No Known Activations