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

    Neuronpedia

    INDEX
    Explanations

    causality, equality, Infinity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     চট্ট
    0.39
     convexo
    0.38
     astute
    0.38
    ප
    0.37
    ቴ
    0.37
     दशमलव
    0.37
    装
    0.36
    PK
    0.36
    िश्च
    0.35
     ck
    0.35
    POSITIVE LOGITS
    BinaryOperation
    0.43
     Suiza
    0.42
     Eugene
    0.40
    ALTERN
    0.40
    ედერ
    0.40
    ාවිත
    0.39
     Toggle
    0.38
    砾
    0.38
    ›
    0.38
    Toggle
    0.37
    Act Density 0.000%

    No Known Activations