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

    Neuronpedia

    INDEX
    Explanations

    HTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Repository
    -0.07
    银行
    -0.06
     Valk
    -0.06
     academy
    -0.06
     Library
    -0.06
     Tags
    -0.06
     dangers
    -0.06
     Lang
    -0.06
     left
    -0.06
     ListView
    -0.06
    POSITIVE LOGITS
    |()↵
    0.07
    ้งาน
    0.07
    Nr
    0.07
    sted
    0.07
     hebt
    0.06
     reimburse
    0.06
    bian
    0.06
     pf
    0.06
     nửa
    0.06
    ()↵↵↵↵
    0.06
    Act Density 0.011%

    No Known Activations