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

    Neuronpedia

    INDEX
    Explanations

    Code/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     củ
    -0.07
     reloading
    -0.07
     officers
    -0.06
    !”↵↵
    -0.06
     queens
    -0.06
     Bern
    -0.06
     Kashmir
    -0.06
    Omega
    -0.06
     glam
    -0.06
    ubuntu
    -0.06
    POSITIVE LOGITS
    InstantiationException
    0.07
     рук
    0.07
    \Desktop
    0.07
    objc
    0.07
    eryl
    0.07
    考试
    0.07
    swing
    0.07
     Οκ
    0.06
     soutěže
    0.06
     빈
    0.06
    Act Density 0.000%

    No Known Activations