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

    Neuronpedia

    INDEX
    Explanations

    Expressing sympathy/apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    masına
    -0.07
     pauses
    -0.07
     Powder
    -0.06
    การส
    -0.06
    dry
    -0.06
    MOOTH
    -0.06
    äs
    -0.06
     bloque
    -0.06
    泊
    -0.06
    เต
    -0.06
    POSITIVE LOGITS
     т
    0.06
    (u
    0.06
     dereg
    0.06
    ihu
    0.06
                    
    0.06
     complaint
    0.06
    Consider
    0.05
    DD
    0.05
    вести
    0.05
    (program
    0.05
    Act Density 0.011%

    No Known Activations