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

    Neuronpedia

    INDEX
    Explanations

    suppression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     escape
    -0.08
     scientific
    -0.08
     amper
    -0.08
     Reson
    -0.08
    -0.08
     proportional
    -0.08
     resonance
    -0.08
    让我
    -0.08
     Breit
    -0.08
     escapes
    -0.08
    POSITIVE LOGITS
    -package
    0.10
     tiger
    0.09
     mulch
    0.09
     landscaping
    0.08
    maintenance
    0.08
     discouraged
    0.08
     шару
    0.08
     nuisance
    0.08
    orgon
    0.08
     shrubs
    0.08
    Act Density 0.006%

    No Known Activations