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
    $fields
    -0.07
    Keyboard
    -0.07
     scouts
    -0.06
    898
    -0.06
    ้าร
    -0.06
     Presidents
    -0.06
    tığ
    -0.06
     crops
    -0.06
    クラブ
    -0.06
    pkt
    -0.06
    POSITIVE LOGITS
    _jwt
    0.07
    allax
    0.07
    TABLE
    0.06
    unded
    0.06
     dhe
    0.06
     }))↵
    0.06
     }]↵
    0.06
     san
    0.06
     риз
    0.06
     spp
    0.06
    Act Density 0.006%

    No Known Activations