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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simplistic
    -0.07
    /to
    -0.07
    跨界
    -0.07
    -commit
    -0.06
     tend
    -0.06
     need
    -0.06
    -tr
    -0.06
    /reg
    -0.06
     غ
    -0.06
    /com
    -0.06
    POSITIVE LOGITS
    当地
    0.07
    海淀
    0.07
     deutsch
    0.07
     france
    0.07
    unan
    0.07
    }{$
    0.07
     кроме
    0.07
     renew
    0.07
    akter
    0.07
     Decrypt
    0.07
    Act Density 0.003%

    No Known Activations