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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    departure
    -0.08
    badge
    -0.07
    (version
    -0.07
    床
    -0.07
    -theme
    -0.06
    .creator
    -0.06
    -net
    -0.06
    위원회
    -0.06
     dây
    -0.06
    دارة
    -0.06
    POSITIVE LOGITS
     insanlar
    0.06
    �
    0.06
    okable
    0.06
     obl
    0.06
     Account
    0.06
    ван
    0.06
     monster
    0.06
     slender
    0.06
     allen
    0.06
    _probe
    0.06
    Act Density 0.013%

    No Known Activations