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

    Neuronpedia

    INDEX
    Explanations

    large quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endanger
    -0.08
     any
    -0.07
    uste
    -0.07
     altogether
    -0.07
     Vista
    -0.06
    pression
    -0.06
    感情
    -0.06
     ليس
    -0.06
     Inform
    -0.06
    _CONFIG
    -0.06
    POSITIVE LOGITS
     estimate
    0.07
    Lt
    0.07
    ]:
↵
    0.07
     afin
    0.07
    \)
    0.07
    blockquote
    0.06
    (from
    0.06
    Eu
    0.06
    Sz
    0.06
     fd
    0.06
    Act Density 0.048%

    No Known Activations