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

    Neuronpedia

    INDEX
    Explanations

    court cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     withstand
    -0.06
     above
    -0.06
     André
    -0.06
    orpion
    -0.06
     Jason
    -0.06
     relax
    -0.06
    foobar
    -0.06
     Men
    -0.06
     Ride
    -0.06
     folklore
    -0.06
    POSITIVE LOGITS
     confidential
    0.07
     gaz
    0.06
    /sbin
    0.06
     incremental
    0.06
     TextField
    0.06
    breaking
    0.06
     classNames
    0.06
    Ended
    0.06
    (!_
    0.06
     STRUCT
    0.06
    Act Density 0.003%

    No Known Activations