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

    Neuronpedia

    INDEX
    Explanations

    actions or events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -has
    -0.07
    -dismissible
    -0.07
     beers
    -0.07
    工
    -0.06
    .bs
    -0.06
     tens
    -0.06
     and
    -0.06
    manship
    -0.06
    leme
    -0.06
    leyen
    -0.06
    POSITIVE LOGITS
    ":"
    0.06
     B
    0.06
    内の
    0.06
     mMap
    0.06
    ltk
    0.06
    urlencode
    0.06
    usize
    0.06
     Chicago
    0.06
    hattan
    0.06
    Death
    0.06
    Act Density 0.370%

    No Known Activations