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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Snapshot
    -0.07
     unit
    -0.07
     incons
    -0.07
    .examples
    -0.07
     meats
    -0.06
    territ
    -0.06
     precip
    -0.06
    xn
    -0.06
     queries
    -0.06
    getString
    -0.06
    POSITIVE LOGITS
     допомаг
    0.07
    _aligned
    0.06
     */)
    0.06
    、↵
    0.06
    بوب
    0.06
    agnostics
    0.05
     Ç
    0.05
     acceptable
    0.05
     Leonardo
    0.05
    MING
    0.05
    Act Density 0.012%

    No Known Activations