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

    Neuronpedia

    INDEX
    Explanations

    geometric points and segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    semantics
    0.44
    。
    0.42
    creen
    0.40
    netics
    0.39
    বর্তন
    0.39
    тер
    0.38
    rolet
    0.38
    .,
    0.38
     Respons
    0.38
    Notably
    0.38
    POSITIVE LOGITS
     wasn
    0.48
     slits
    0.47
     from
    0.45
    ен
    0.45
     antlers
    0.44
    م
    0.43
    ो
    0.42
     on
    0.42
     beads
    0.42
    િંગ
    0.42
    Act Density 0.001%

    No Known Activations