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

    Neuronpedia

    INDEX
    Explanations

    Code/numerical strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    췃
    -0.07
    赊
    -0.07
    鳜
    -0.07
    #ga
    -0.07
    创业
    -0.07
     labeled
    -0.07
     marked
    -0.07
    物料
    -0.07
    三大
    -0.07
    .GetString
    -0.06
    POSITIVE LOGITS
     validations
    0.07
     Ook
    0.07
     ]);↵↵
    0.07
    淑
    0.07
     حيث
    0.07
    甦
    0.06
    ysts
    0.06
    biz
    0.06
     beverages
    0.06
     Tokyo
    0.06
    Act Density 0.077%

    No Known Activations