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

    Neuronpedia

    INDEX
    Explanations

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Big
    0.39
    Powerful
    0.39
    一系列
    0.38
    Nothing
    0.36
     갖
    0.36
     infantil
    0.35
     அவ்வ
    0.35
     Too
    0.35
     mấy
    0.34
     Biggest
    0.34
    POSITIVE LOGITS
     large
    0.67
     lot
    0.66
     fair
    0.63
     multitude
    0.58
     ton
    0.56
     majority
    0.55
    large
    0.54
     disproportion
    0.53
     staggering
    0.52
     considerable
    0.52
    Act Density 0.235%

    No Known Activations