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

    Neuronpedia

    INDEX
    Explanations

    America

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pitt
    -0.08
     Confidence
    -0.07
     Insurance
    -0.07
    网吧
    -0.07
     Dod
    -0.07
    Ns
    -0.07
    ivet
    -0.07
    Floor
    -0.07
    拦截
    -0.06
    implicit
    -0.06
    POSITIVE LOGITS
     DataGridViewCellStyle
    0.08
    >()↵
    0.07
    全国
    0.07
     "'.
    0.07
     colonies
    0.07
    Commands
    0.07
     territories
    0.06
     ministries
    0.06
     developer
    0.06
    🎀
    0.06
    Act Density 0.008%

    No Known Activations