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

    Neuronpedia

    INDEX
    Explanations

    peak flux, ML, search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kobayashi
    0.44
     среде
    0.42
     pulsar
    0.40
     нис
    0.40
    май
    0.38
     baseApiPath
    0.38
    0.38
    Amerika
    0.38
    ()">
    0.38
    ateau
    0.38
    POSITIVE LOGITS
    sometimes
    0.45
     sometimes
    0.43
    ssen
    0.36
    agn
    0.36
     vand
    0.36
     manchmal
    0.36
    consc
    0.36
    ༅
    0.36
     sel
    0.36
     رکن
    0.36
    Act Density 0.000%

    No Known Activations