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

    Neuronpedia

    INDEX
    Explanations

    sports fouls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usage
    -0.07
     air
    -0.07
     Defense
    -0.07
    sharing
    -0.07
     man
    -0.07
     Silver
    -0.07
    _LOGGER
    -0.06
     work
    -0.06
    险
    -0.06
    掘
    -0.06
    POSITIVE LOGITS
     slideshow
    0.07
     modifies
    0.07
     checkboxes
    0.07
     international
    0.07
    ernational
    0.07
    ModelAttribute
    0.07
    ollapse
    0.07
    $post
    0.07
     dictated
    0.07
    _IDLE
    0.07
    Act Density 0.021%

    No Known Activations