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

    Neuronpedia

    INDEX
    Explanations

    enerate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Concent
    -0.07
     rond
    -0.07
     eid
    -0.07
     TX
    -0.06
     Loss
    -0.06
    Nome
    -0.06
     grande
    -0.06
     rhyth
    -0.06
    574
    -0.06
    _hero
    -0.06
    POSITIVE LOGITS
    enerate
    0.14
    generate
    0.08
    .Sm
    0.08
    ("[
    0.07
     glEnd
    0.07
    elop
    0.07
    स
    0.07
    _unregister
    0.07
    _generate
    0.06
    -seat
    0.06
    Act Density 0.002%

    No Known Activations