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

    Neuronpedia

    INDEX
    Explanations

    Bird, scooters, XCHNG

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    هر
    0.61
    经过
    0.57
    耱
    0.53
    нын
    0.52
    رس
    0.51
     име
    0.48
     один
    0.48
    ار
    0.48
    三分
    0.48
    ون
    0.47
    POSITIVE LOGITS
     ngăn
    0.58
    Biden
    0.58
     essentiels
    0.58
     ২০২২
    0.57
     कोविड
    0.55
     COVID
    0.53
     Biden
    0.52
    🥵
    0.52
    Ky
    0.51
     pandemia
    0.51
    Act Density 0.750%

    No Known Activations