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

    Neuronpedia

    INDEX
    Explanations

    building concepts and their implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जांच
    0.45
     multil
    0.40
     කරන
    0.39
     Brazilian
    0.39
     glTexParameteri
    0.38
     factorial
    0.38
     russian
    0.38
     affiliations
    0.38
     dynamics
    0.37
     investigators
    0.37
    POSITIVE LOGITS
     раство
    0.47
    ืน
    0.46
    umption
    0.42
    зив
    0.42
    Sunday
    0.42
    estate
    0.41
    aree
    0.41
     Riverside
    0.41
    amounts
    0.41
    प्रदेश
    0.40
    Act Density 0.010%

    No Known Activations