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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     customized
    -0.08
     Leone
    -0.07
     NEGLIGENCE
    -0.07
    StringEncoding
    -0.07
    олева
    -0.07
     Jaguars
    -0.06
     Dialogue
    -0.06
     Daw
    -0.06
    (login
    -0.06
     Qualcomm
    -0.06
    POSITIVE LOGITS
     atte
    0.06
     �
    0.06
     구조
    0.06
     nek
    0.06
     заход
    0.06
     البل
    0.06
     olmam
    0.05
    하였다
    0.05
    �
    0.05
     çevir
    0.05
    Act Density 0.007%

    No Known Activations