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

    Neuronpedia

    INDEX
    Explanations

    shader compile and link status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ုတ်
    0.40
     staggered
    0.40
     Quasi
    0.40
     मांड
    0.39
     uplift
    0.38
    ลา
    0.38
     Upl
    0.38
     листо
    0.37
     Москов
    0.37
    協
    0.37
    POSITIVE LOGITS
    link
    0.55
     link
    0.53
    attach
    0.51
     info
    0.50
     attach
    0.50
     Link
    0.49
    COMPILE
    0.48
    info
    0.48
     compile
    0.46
    Link
    0.46
    Act Density 0.004%

    No Known Activations