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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phenomenon
    -0.06
     postal
    -0.06
     많
    -0.06
    装置
    -0.06
     tốc
    -0.06
    证券
    -0.06
     BaseActivity
    -0.06
    immutable
    -0.06
     conception
    -0.06
     glo
    -0.06
    POSITIVE LOGITS
    -focused
    0.07
     skim
    0.07
    promo
    0.07
     yogurt
    0.06
     aggi
    0.06
     Unsupported
    0.06
    layer
    0.06
     nebude
    0.06
    '))↵↵↵
    0.06
     Hij
    0.06
    Act Density 0.000%

    No Known Activations