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

    Neuronpedia

    INDEX
    Explanations

    named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pip
    -0.06
    nip
    -0.06
     gam
    -0.06
    ucu
    -0.06
    :{}
    -0.06
    ham
    -0.06
     NIC
    -0.06
    nou
    -0.06
     hun
    -0.06
    ип
    -0.06
    POSITIVE LOGITS
    θη
    0.07
     apology
    0.07
     McGu
    0.07
    _PATTERN
    0.07
    imeInterval
    0.06
    .fragments
    0.06
    Bước
    0.06
    .tabPage
    0.06
    Truth
    0.06
    (CultureInfo
    0.06
    Act Density 0.050%

    No Known Activations