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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kindness
    -0.08
    ിരുന്ന
    -0.08
    ckeditor
    -0.08
    �
    -0.07
     adip
    -0.07
    ిస్త
    -0.07
     sociedade
    -0.07
    กีฬา
    -0.07
     glæ
    -0.07
    hei
    -0.07
    POSITIVE LOGITS
     exited
    0.08
     changed
    0.08
     stalled
    0.08
    cakes
    0.07
     Gates
    0.07
     Renaissance
    0.07
     Apartments
    0.07
     Quem
    0.07
     Brokerage
    0.07
    quests
    0.07
    Act Density 0.002%

    No Known Activations