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

    Neuronpedia

    INDEX
    Explanations

    miðlar, protathlima, ióspóros, hidróxido

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    에게
    0.25
    єї
    0.25
    Rational
    0.24
    ్రె
    0.24
    ners
    0.23
    ("
    0.22
    raine
    0.22
    vature
    0.22
    s
    0.22
    вають
    0.22
    POSITIVE LOGITS
    ূপে
    0.30
     miglior
    0.27
     miner
    0.25
     فريبي
    0.25
    ர்களையும்
    0.25
    ilización
    0.25
     xạ
    0.25
    offe
    0.24
    ac
    0.24
     করেছিলাম
    0.24
    Act Density 0.104%

    No Known Activations