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

    Neuronpedia

    INDEX
    Explanations

    say "B"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulist
    -0.09
     yüz
    -0.07
    .setInput
    -0.07
    aukee
    -0.07
    �
    -0.07
    )?$
    -0.07
    쩼
    -0.07
     sextreffen
    -0.07
    “What
    -0.07
    "]/
    -0.06
    POSITIVE LOGITS
     tir
    0.08
    ulan
    0.08
     manipulated
    0.07
    าว
    0.07
     mk
    0.07
    可信
    0.07
     CoreData
    0.06
    vl
    0.06
    新华
    0.06
    这些都是
    0.06
    Act Density 0.001%

    No Known Activations