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

    Neuronpedia

    INDEX
    Explanations

    Detachment and observation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dark
    -0.08
     stall
    -0.08
     drivetrain
    -0.08
     duo
    -0.07
    ements
    -0.07
    ữ
    -0.07
     collaboration
    -0.07
     keyword
    -0.07
     deadline
    -0.07
     dedication
    -0.07
    POSITIVE LOGITS
     vantage
    0.10
     asupra
    0.09
    窥
    0.09
    看
    0.09
     взгля
    0.09
    -headed
    0.08
     distancing
    0.08
    త్య
    0.08
    来看
    0.08
     바라
    0.08
    Act Density 0.015%

    No Known Activations