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

    Neuronpedia

    INDEX
    Explanations

    fortified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ubmit
    -0.08
     elusive
    -0.08
     obstacles
    -0.08
     strict
    -0.07
     daunting
    -0.07
    Muse
    -0.07
    inite
    -0.07
    orius
    -0.07
    оз
    -0.07
    oje
    -0.07
    POSITIVE LOGITS
     செய்யப்பட்ட
    0.08
    <?↵
    0.08
     precipitation
    0.08
     edition
    0.08
     enrichment
    0.08
     infused
    0.07
     supplementation
    0.07
     Aux
    0.07
    .aggregate
    0.07
     künst
    0.07
    Act Density 0.004%

    No Known Activations