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

    Neuronpedia

    INDEX
    Explanations

    resent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    warnings
    -0.07
    芸
    -0.07
     lookout
    -0.07
    (argument
    -0.07
    _style
    -0.06
    .pause
    -0.06
    navbarSupportedContent
    -0.06
    Sus
    -0.06
     bed
    -0.06
     HttpNotFound
    -0.06
    POSITIVE LOGITS
     resentment
    0.10
    全员
    0.08
     recipient
    0.07
     먼저
    0.07
     đoàn
    0.07
    することで
    0.07
    (_)
    0.07
    新技术
    0.07
    多く
    0.07
    ipients
    0.07
    Act Density 0.003%

    No Known Activations