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

    Neuronpedia

    INDEX
    Explanations

    card games, orientation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     \$
    -0.07
     Hive
    -0.07
    -ps
    -0.06
     shader
    -0.06
     pohled
    -0.06
     fundamentals
    -0.06
    арат
    -0.06
     QC
    -0.06
     GBP
    -0.06
    职业
    -0.06
    POSITIVE LOGITS
    (exec
    0.07
    spy
    0.07
    ]]↵↵
    0.06
     eskorte
    0.06
    ノ
    0.06
     nod
    0.06
    şk
    0.06
    !!}</
    0.06
    maj
    0.06
    `);↵↵
    0.06
    Act Density 0.014%

    No Known Activations