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

    Neuronpedia

    INDEX
    Explanations

    cacheability and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idP
    0.39
    θ
    0.38
     pelajaran
    0.38
    Ids
    0.37
     राजद
    0.37
    Deaths
    0.37
    োর্ট
    0.36
    궁
    0.35
     tartar
    0.35
    Ideas
    0.35
    POSITIVE LOGITS
     dobu
    0.48
     durations
    0.44
     absoluto
    0.41
     மணி
    0.40
     Expires
    0.40
     durée
    0.39
    expires
    0.39
    Expires
    0.39
     expired
    0.38
    ーン
    0.38
    Act Density 0.002%

    No Known Activations