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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     against
    1.21
     Against
    1.21
    Against
    1.10
    against
    1.10
     împ
    0.97
     против
    0.93
     AGAINST
    0.92
     gegen
    0.89
    gegen
    0.84
     tegen
    0.79
    POSITIVE LOGITS
     stuck
    0.70
     चक्रवृद्धि
    0.68
     које
    0.67
    ynchronously
    0.67
     které
    0.66
     hit
    0.65
     দলের
    0.65
    CHEC
    0.65
     लॉगिन
    0.64
    ूहिक
    0.63
    Act Density 0.003%

    No Known Activations