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

    Neuronpedia

    INDEX
    Explanations

    ast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nuevo
    -0.07
     VM
    -0.06
     currency
    -0.06
     멀
    -0.06
     Irene
    -0.06
     eğer
    -0.06
     number
    -0.06
     paranoid
    -0.06
    YL
    -0.06
     station
    -0.06
    POSITIVE LOGITS
     kabil
    0.08
    )")↵↵
    0.06
     expiresIn
    0.06
    )]);↵
    0.06
    ])]↵
    0.06
    )");↵
    0.06
     oblast
    0.06
    !";
↵
    0.06
    طه
    0.06
    ]='\
    0.06
    Act Density 0.001%

    No Known Activations