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

    Neuronpedia

    INDEX
    Explanations

    1. Understand the Equivalence Point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     remedied
    0.44
     మూ
    0.42
     ridiculed
    0.42
     startled
    0.40
     crumbled
    0.40
     evaded
    0.40
     remedy
    0.39
     comprobar
    0.39
     trampled
    0.39
    arrayList
    0.39
    POSITIVE LOGITS
     Oil
    0.45
     Race
    0.44
    ોર્ટ
    0.44
    Race
    0.43
    ORTH
    0.43
     Optim
    0.42
     Optimization
    0.42
    𝗘
    0.42
     Science
    0.41
    RI
    0.41
    Act Density 0.006%

    No Known Activations