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

    Neuronpedia

    INDEX
    Explanations

    path

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áž
    -0.08
    чес
    -0.07
    _syntax
    -0.07
    emed
    -0.07
     dracon
    -0.07
     axes
    -0.07
    POCH
    -0.07
    CEO
    -0.07
     Sob
    -0.07
    ONS
    -0.07
    POSITIVE LOGITS
     updater
    0.06
    dığında
    0.06
    screen
    0.06
     pave
    0.06
    ，可以
    0.05
     проц
    0.05
     supermarket
    0.05
     GPI
    0.05
    ('{
    0.05
     crashing
    0.05
    Act Density 0.023%

    No Known Activations