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

    Neuronpedia

    INDEX
    Explanations

    references to happiness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    keepers
    -0.07
    houses
    -0.07
     elimination
    -0.07
     suspicions
    -0.07
    now
    -0.07
     decomposition
    -0.07
    ambio
    -0.06
     NOW
    -0.06
     delays
    -0.06
     requests
    -0.06
    POSITIVE LOGITS
     heure
    0.08
    Featured
    0.07
     τον
    0.07
    être
    0.06
    >;
↵
    0.06
     τρα
    0.06
    .exist
    0.06
    なた
    0.06
    ποι
    0.06
     phúc
    0.06
    Act Density 0.012%

    No Known Activations