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

    Neuronpedia

    INDEX
    Explanations

    news quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     efter
    -0.06
    ‪
    -0.06
    ्रथ
    -0.06
     inward
    -0.06
    alled
    -0.06
     deactivate
    -0.06
    domain
    -0.06
     away
    -0.06
     딸
    -0.06
     mortality
    -0.06
    POSITIVE LOGITS
     arthritis
    0.07
     Glow
    0.07
     examiner
    0.07
    금
    0.07
    фици
    0.06
    اسي
    0.06
    OLOR
    0.06
    _WITH
    0.06
    abcdef
    0.06
    .addr
    0.06
    Act Density 0.046%

    No Known Activations