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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duffy
    -0.08
     sicher
    -0.07
    :user
    -0.07
     amino
    -0.07
    ➧
    -0.07
    /tty
    -0.07
    sign
    -0.07
     Hubbard
    -0.07
     hazardous
    -0.07
     xử
    -0.06
    POSITIVE LOGITS
    챤
    0.07
     gives
    0.07
    打破了
    0.07
     Returns
    0.07
    pon
    0.07
    principal
    0.07
    iotic
    0.06
    醒了
    0.06
    skill
    0.06
    瓶子
    0.06
    Act Density 0.006%

    No Known Activations