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

    Neuronpedia

    INDEX
    Explanations

    code object type checking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pipe
    -0.07
     От
    -0.07
     kayıt
    -0.07
     built
    -0.07
    也有
    -0.07
     swords
    -0.06
     sau
    -0.06
    ligne
    -0.06
     JADX
    -0.06
    ango
    -0.06
    POSITIVE LOGITS
    ="""
    0.07
     �
    0.07
     đị
    0.06
     broadcaster
    0.06
    ************************************************************************
    0.06
     Acrobat
    0.06
    Eth
    0.06
    ایج
    0.06
    itioner
    0.06
     Dol
    0.06
    Act Density 0.031%

    No Known Activations