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

    Neuronpedia

    INDEX
    Explanations

    programming languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    》《
    0.34
    ަތ
    0.32
    ῦ
    0.31
    }$}
    0.31
     isotopes
    0.31
    ˆ
    0.31
     वनडे
    0.30
    KA
    0.29
     annealed
    0.29
    舷
    0.29
    POSITIVE LOGITS
    лександр
    0.39
     USS
    0.39
     titular
    0.35
     Ubuy
    0.35
    judul
    0.33
     chiế
    0.32
     Thos
    0.32
     فه
    0.32
     GDPPC
    0.32
    nemis
    0.32
    Act Density 0.075%

    No Known Activations