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

    Neuronpedia

    INDEX
    Explanations

    San Francisco politics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’de
    -0.07
     리스트
    -0.07
     unwind
    -0.07
    КА
    -0.07
    cdb
    -0.06
     Rakou
    -0.06
    ’ya
    -0.06
    Radians
    -0.06
    ctrine
    -0.06
    grid
    -0.06
    POSITIVE LOGITS
     ousted
    0.07
     AVL
    0.07
    �
    0.06
     epis
    0.06
     मल
    0.06
     terrestrial
    0.06
     towering
    0.06
     undermined
    0.06
     Iv
    0.06
    σιμο
    0.06
    Act Density 0.006%

    No Known Activations