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

    Neuronpedia

    INDEX
    Explanations

    new game content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вк
    -0.07
    真
    -0.06
     дозвол
    -0.06
    �
    -0.06
     IDS
    -0.06
    ip
    -0.06
    aec
    -0.06
     زی
    -0.06
     hjem
    -0.06
     Rena
    -0.06
    POSITIVE LOGITS
    _linked
    0.07
    Μ
    0.07
    .activity
    0.07
    Bonus
    0.07
     ENGINE
    0.07
     resale
    0.06
     SHIFT
    0.06
    50
    0.06
    paredStatement
    0.06
     spare
    0.06
    Act Density 0.022%

    No Known Activations