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

    Neuronpedia

    INDEX
    Explanations

    protecting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    हासन
    0.64
     प्रमेय
    0.63
     cucumbers
    0.59
    Pdf
    0.58
     लेसन
    0.57
    শিক
    0.57
    vođa
    0.57
    lsulfanyl
    0.56
    lewati
    0.56
     সরানো
    0.56
    POSITIVE LOGITS
    continu
    0.68
     Represent
    0.58
     Protect
    0.57
     Protecting
    0.56
     représenter
    0.55
     protect
    0.55
     continu
    0.55
     représent
    0.54
     Pert
    0.54
    ऱ
    0.53
    Act Density 0.000%

    No Known Activations