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

    Neuronpedia

    INDEX
    Explanations

    Site

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >

↵
    -0.06
     memes
    -0.06
     developed
    -0.06
     Schw
    -0.06
    >User
    -0.06
    .signals
    -0.06
    科技
    -0.06
     flop
    -0.06
     growth
    -0.06
    wh
    -0.06
    POSITIVE LOGITS
     теат
    0.07
     unconditional
    0.06
     �
    0.06
     урок
    0.06
    іти
    0.06
    ควร
    0.06
    !")
    0.06
     дів
    0.06
     obsahuje
    0.06
     hinter
    0.06
    Act Density 0.002%

    No Known Activations