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

    Neuronpedia

    INDEX
    Explanations

    Left

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uk
    0.47
    ely
    0.46
    ihl
    0.45
    erven
    0.44
    ingu
    0.44
    trusted
    0.44
    ub
    0.43
    tiene
    0.43
    سون
    0.43
    ahy
    0.43
    POSITIVE LOGITS
     outlook
    0.46
     ސ
    0.44
     preços
    0.44
     governments
    0.44
     показывает
    0.43
     viscose
    0.43
     reshape
    0.42
     prices
    0.42
     overall
    0.42
     eagles
    0.41
    Act Density 0.000%

    No Known Activations