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

    Neuronpedia

    INDEX
    Explanations

    algebraic expressions and equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tjiwarl
    0.61
    ियारों
    0.52
    gramModel
    0.51
     CCOC
    0.50
    Therates
    0.50
     Bạch
    0.50
    尕
    0.50
    চৈত
    0.50
    ხვევ
    0.50
     mortgagee
    0.50
    POSITIVE LOGITS
    0
    0.71
    (
    0.69
    +
    0.69
    x
    0.68
    k
    0.68
    n
    0.66
    v
    0.66
    ·
    0.66
    g
    0.66
     +
    0.65
    Act Density 0.067%

    No Known Activations