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

    Neuronpedia

    INDEX
    Explanations

    replacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     speeches
    -0.07
     Bright
    -0.07
     sleepy
    -0.07
    Bright
    -0.07
     advisers
    -0.07
     "("
    -0.07
    限
    -0.06
     trunk
    -0.06
     바이
    -0.06
    NASA
    -0.06
    POSITIVE LOGITS
    ()?;↵
    0.06
    \Traits
    0.06
    =""↵
    0.06
    .UNRELATED
    0.06
    。
↵
    0.06
    ({})↵
    0.06
    _PLL
    0.06
    )];↵
    0.06
    _converter
    0.06
    discard
    0.06
    Act Density 0.001%

    No Known Activations