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

    Neuronpedia

    INDEX
    Explanations

    8

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    율
    -0.07
    .Condition
    -0.06
    WebDriver
    -0.06
     condemnation
    -0.06
    spinner
    -0.06
     provinces
    -0.06
    Website
    -0.06
    bett
    -0.06
    Towards
    -0.06
    ede
    -0.06
    POSITIVE LOGITS
     ipc
    0.07
     pants
    0.07
    ór
    0.07
     murm
    0.06
    _bus
    0.06
     Abr
    0.06
     термін
    0.06
     Rak
    0.06
     nemůže
    0.06
    @mail
    0.06
    Act Density 0.006%

    No Known Activations