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

    Neuronpedia

    INDEX
    Explanations

    AI, legal, choose, define, similar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Price
    0.43
     Harga
    0.42
     સં
    0.41
     Buyer
    0.41
     قائمة
    0.41
    шов
    0.38
     Sergio
    0.38
    谤
    0.38
     Purch
    0.38
     Togo
    0.37
    POSITIVE LOGITS
    Screw
    0.43
     문제입니다
    0.39
    DbType
    0.37
    proble
    0.35
    Fock
    0.35
    variety
    0.35
     Screw
    0.35
    kind
    0.34
    কল
    0.34
    㕫
    0.34
    Act Density 0.000%

    No Known Activations