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

    Neuronpedia

    INDEX
    Explanations

    traditional banking, reliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TINGS
    0.47
     desej
    0.41
    Ư
    0.41
    頭髮
    0.39
    ﺩ
    0.39
    গম
    0.38
    dì
    0.38
    ଟି
    0.38
     desires
    0.38
    past
    0.38
    POSITIVE LOGITS
    ^(
    0.42
    __()
    0.39
     met
    0.39
    的基础上
    0.38
     program
    0.37
     aut
    0.36
     organization
    0.36
     Derivative
    0.36
     dots
    0.36
     unst
    0.36
    Act Density 0.000%

    No Known Activations