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

    Neuronpedia

    INDEX
    Explanations

    Okay, Alright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    puts
    0.84
    válto
    0.79
    inate
    0.75
    defines
    0.74
    printf
    0.73
    objective
    0.72
    name
    0.71
    title
    0.71
    test
    0.70
    rup
    0.70
    POSITIVE LOGITS
     Jupyter
    0.96
     Tjiwarl
    0.92
     Ansible
    0.88
     Overwatch
    0.87
     Aplikasi
    0.87
     shenanigans
    0.84
     Macbook
    0.84
     Peloton
    0.83
     qPCR
    0.83
     PFAS
    0.83
    Act Density 0.059%

    No Known Activations