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

    Neuronpedia

    INDEX
    Explanations

    rule

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Type
    -0.07
    Density
    -0.07
    actions
    -0.07
    News
    -0.07
    欧美
    -0.07
    newInstance
    -0.07
     Vậy
    -0.07
     bestselling
    -0.06
    bsites
    -0.06
    tools
    -0.06
    POSITIVE LOGITS
     rule
    0.14
    -rule
    0.08
     rulers
    0.08
     Rule
    0.08
     RULE
    0.08
     rules
    0.08
     ruler
    0.07
    rule
    0.06
     Cook
    0.06
    (rule
    0.06
    Act Density 0.009%

    No Known Activations