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

    Neuronpedia

    INDEX
    Explanations

    becomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (tx
    -0.07
     Belfast
    -0.06
    [str
    -0.06
     Tantra
    -0.06
    temporary
    -0.06
    ares
    -0.06
     期
    -0.06
     Boiler
    -0.06
    finder
    -0.06
    위원
    -0.06
    POSITIVE LOGITS
     becomes
    0.09
     замі
    0.07
     loses
    0.06
     информации
    0.06
     possessions
    0.06
    となり
    0.06
     emblem
    0.06
     novamente
    0.06
     northeast
    0.06
     scrollbar
    0.06
    Act Density 0.071%

    No Known Activations