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

    Neuronpedia

    INDEX
    Explanations

    current status and ongoing tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нус
    0.53
     addicts
    0.51
     railings
    0.48
     omissions
    0.47
    硬件
    0.46
     anglers
    0.44
     alcoholism
    0.44
     aos
    0.44
     aneurysm
    0.44
    姆斯
    0.43
    POSITIVE LOGITS
    strnc
    0.49
    convers
    0.45
    ov
    0.44
    th
    0.43
    rot
    0.43
    ijd
    0.43
    waan
    0.43
    emat
    0.42
    isting
    0.42
    atka
    0.42
    Act Density 0.001%

    No Known Activations