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

    Neuronpedia

    INDEX
    Explanations

    join/joined

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expect
    -0.07
     Ct
    -0.07
    Could
    -0.07
     lengthy
    -0.07
     tweaking
    -0.06
     Could
    -0.06
     convers
    -0.06
    _topic
    -0.06
    -Ф
    -0.06
    (flag
    -0.06
    POSITIVE LOGITS
     joins
    0.08
     joined
    0.08
    結婚
    0.07
     моб
    0.07
     JOIN
    0.07
     join
    0.07
    eroon
    0.07
     joining
    0.07
    بع
    0.06
    案
    0.06
    Act Density 0.020%

    No Known Activations