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

    Neuronpedia

    INDEX
    Explanations

    scientific results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tv
    -0.07
    jer
    -0.07
     Godzilla
    -0.06
     forma
    -0.06
    Mag
    -0.06
     configur
    -0.06
    Min
    -0.06
    era
    -0.06
     Maria
    -0.06
    errupted
    -0.06
    POSITIVE LOGITS
    /controller
    0.08
    旅行
    0.06
     pry
    0.06
     осві
    0.06
     queryString
    0.06
    RED
    0.06
    .GridColumn
    0.06
     Solution
    0.06
    BaseContext
    0.06
        
    0.05
    Act Density 0.070%

    No Known Activations