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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cross
    -0.07
     Vas
    -0.07
    worm
    -0.06
     subprocess
    -0.06
    оя
    -0.06
     dine
    -0.06
    useRalative
    -0.06
    \grid
    -0.06
     goodbye
    -0.06
    _deploy
    -0.06
    POSITIVE LOGITS
    ρει
    0.07
    istrar
    0.07
    Explorer
    0.07
    Systems
    0.06
    (IR
    0.06
     disastrous
    0.06
     listing
    0.06
    eltas
    0.06
    lü
    0.06
    (PATH
    0.06
    Act Density 0.000%

    No Known Activations