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

    Neuronpedia

    INDEX
    Explanations

    _layout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sheltered
    -0.08
     stalking
    -0.08
     الشرطة
    -0.08
    Faction
    -0.08
    vap
    -0.08
     стрел
    -0.07
    CO
    -0.07
     nitrate
    -0.07
     naï
    -0.07
    Retail
    -0.07
    POSITIVE LOGITS
    _finalize
    0.08
     ứng
    0.08
     decorations
    0.08
     finalize
    0.08
    areness
    0.07
     scheduler
    0.07
    leanup
    0.07
     бү
    0.07
     compensate
    0.07
     bho
    0.07
    Act Density 0.001%

    No Known Activations