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

    Neuronpedia

    INDEX
    Explanations

    patent office

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     if
    0.47
     hacerlo
    0.47
    קום
    0.47
    Leben
    0.45
     continuando
    0.41
     కొన
    0.41
    zeitig
    0.40
    .”
    0.40
     atacar
    0.40
     продолжи
    0.38
    POSITIVE LOGITS
    cInfo
    0.42
    িকাংশ
    0.38
     precept
    0.38
    dS
    0.38
    ds
    0.38
     workers
    0.38
     万
    0.38
    umpang
    0.38
    *****",
    0.38
    createdBy
    0.38
    Act Density 0.001%

    No Known Activations